Search Results for author: Yi Ma

Found 133 papers, 52 papers with code

Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription

no code implementations16 Mar 2024 Hongxiang Zhao, Xili Dai, Jianan Wang, Shengbang Tong, Jingyuan Zhang, Weida Wang, Lei Zhang, Yi Ma

This consequently limits the performance of downstream tasks, such as image-to-multiview generation and 3D reconstruction.

3D Reconstruction Novel View Synthesis

Differentially Private Representation Learning via Image Captioning

no code implementations4 Mar 2024 Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets.

Image Captioning Representation Learning

Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model

no code implementations27 Feb 2024 Panqi Jia, A. Burakhan Koyuncu, Jue Mao, Ze Cui, Yi Ma, Tiansheng Guo, Timofey Solovyev, Alexander Karabutov, Yin Zhao, Jing Wang, Elena Alshina, Andre Kaup

To generate reconstructed images with the desired bits per pixel and assess the BD-rate performance of both the JPEG-AI verification model and VVC intra, bit rate matching is employed.

Image Compression

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

1 code implementation23 Feb 2024 Chun-Hsiao Yeh, Ta-Ying Cheng, He-Yen Hsieh, Chuan-En Lin, Yi Ma, Andrew Markham, Niki Trigoni, H. T. Kung, Yubei Chen

First, current personalization techniques fail to reliably extend to multiple concepts -- we hypothesize this to be due to the mismatch between complex scenes and simple text descriptions in the pre-training dataset (e. g., LAION).

Image Generation

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

1 code implementation11 Jan 2024 Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann Lecun, Saining Xie

To understand the roots of these errors, we explore the gap between the visual embedding space of CLIP and vision-only self-supervised learning.

Representation Learning Self-Supervised Learning +1

On Chernoff Lower-Bound of Outage Threshold for Non-Central $χ^2$-Distributed Beamforming Gain in URLLC Systems

no code implementations28 Dec 2023 Jinfei Wang, Yi Ma, Rahim Tafazolli, Zhibo Pang

The cumulative distribution function (CDF) of a non-central $\chi^2$-distributed random variable (RV) is often used when measuring the outage probability of communication systems.

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

no code implementations18 Dec 2023 Michael Psenka, Alejandro Escontrela, Pieter Abbeel, Yi Ma

Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning.

reinforcement-learning

EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset

no code implementations13 Dec 2023 Peiqi Duan, Boyu Li, Yixin Yang, Hanyue Lou, Minggui Teng, Yi Ma, Boxin Shi

Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed.

Benchmarking Deblurring +6

White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?

1 code implementation22 Nov 2023 Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma

This leads to a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable.

Data Compression Denoising +1

RLIF: Interactive Imitation Learning as Reinforcement Learning

no code implementations21 Nov 2023 Jianlan Luo, Perry Dong, Yuexiang Zhai, Yi Ma, Sergey Levine

We also provide a unified framework to analyze our RL method and DAgger; for which we present the asymptotic analysis of the suboptimal gap for both methods as well as the non-asymptotic sample complexity bound of our method.

Continuous Control Imitation Learning +1

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

no code implementations1 Nov 2023 Yi Ma, Chenjun Xiao, Hebin Liang, Jianye Hao

Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL).

Decision Making Hierarchical Reinforcement Learning +3

Near and Far Field Model Mismatch: Implications on 6G Communications, Localization, and Sensing

no code implementations10 Oct 2023 Ahmed Elzanaty, Jiuyu Liu, Anna Guerra, Francesco Guidi, Yi Ma, Rahim Tafazolli

The upcoming 6G technology is expected to operate in near-field (NF) radiating conditions thanks to high-frequency and electrically large antenna arrays.

Investigating the Catastrophic Forgetting in Multimodal Large Language Models

no code implementations19 Sep 2023 Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma

However, catastrophic forgetting, a notorious phenomenon where the fine-tuned model fails to retain similar performance compared to the pre-trained model, still remains an inherent problem in multimodal LLMs (MLLM).

Image Classification Language Modelling +1

General In-Hand Object Rotation with Vision and Touch

no code implementations18 Sep 2023 Haozhi Qi, Brent Yi, Sudharshan Suresh, Mike Lambeta, Yi Ma, Roberto Calandra, Jitendra Malik

We introduce RotateIt, a system that enables fingertip-based object rotation along multiple axes by leveraging multimodal sensory inputs.

Object

Emergence of Segmentation with Minimalistic White-Box Transformers

1 code implementation30 Aug 2023 Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu, Druv Pai, Sam Buchanan, Yi Ma

Transformer-like models for vision tasks have recently proven effective for a wide range of downstream applications such as segmentation and detection.

Segmentation Self-Supervised Learning

Canonical Factors for Hybrid Neural Fields

no code implementations ICCV 2023 Brent Yi, Weijia Zeng, Sam Buchanan, Yi Ma

Factored feature volumes offer a simple way to build more compact, efficient, and intepretable neural fields, but also introduce biases that are not necessarily beneficial for real-world data.

On Chernoff Lower-Bound of Outage Threshold for Non-Central $χ^2$-Distributed MIMO Beamforming Gain

no code implementations24 Aug 2023 Jinfei Wang, Yi Ma, Rahim Tafazolli

The cumulative distribution function (CDF) of a non-central $\chi^2$-distributed random variable (RV) is often used when measuring the outage probability of communication systems.

Scaff-PD: Communication Efficient Fair and Robust Federated Learning

no code implementations25 Jul 2023 Yaodong Yu, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan

We present Scaff-PD, a fast and communication-efficient algorithm for distributionally robust federated learning.

Fairness Federated Learning

Pixel-wise Graph Attention Networks for Person Re-identification

1 code implementation18 Jul 2023 Wenyu Zhang, Qing Ding, Jian Hu, Yi Ma, Mingzhe Lu

Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet).

Graph Attention Graph Generation +1

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning

no code implementations27 Jun 2023 Jinyi Liu, Yi Ma, Jianye Hao, Yujing Hu, Yan Zheng, Tangjie Lv, Changjie Fan

In summary, our research emphasizes the significance of trajectory-based data sampling techniques in enhancing the efficiency and performance of offline RL algorithms.

D4RL Offline RL +2

ViP: A Differentially Private Foundation Model for Computer Vision

1 code implementation15 Jun 2023 Yaodong Yu, Maziar Sanjabi, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we propose as a mitigation measure a recipe to train foundation vision models with differential privacy (DP) guarantee.

Improving Offline-to-Online Reinforcement Learning with Q-Ensembles

no code implementations12 Jun 2023 Kai Zhao, Yi Ma, Jianye Hao, Jinyi Liu, Yan Zheng, Zhaopeng Meng

Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience.

Offline RL reinforcement-learning +1

HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach

no code implementations10 Jun 2023 Shixi Lian, Yi Ma, Jinyi Liu, Yan Zheng, Zhaopeng Meng

Offline reinforcement learning (ORL) has gained attention as a means of training reinforcement learning models using pre-collected static data.

D4RL Data Augmentation +1

Iteratively Refined Behavior Regularization for Offline Reinforcement Learning

no code implementations9 Jun 2023 Xiaohan Hu, Yi Ma, Chenjun Xiao, Yan Zheng, Jianye Hao

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution.

D4RL Offline RL +2

Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models

1 code implementation8 Jun 2023 Tianzhe Chu, Shengbang Tong, Tianjiao Ding, Xili Dai, Benjamin David Haeffele, René Vidal, Yi Ma

In this paper, we propose a novel image clustering pipeline that leverages the powerful feature representation of large pre-trained models such as CLIP and cluster images effectively and efficiently at scale.

Clustering Image Clustering +1

White-Box Transformers via Sparse Rate Reduction

1 code implementation NeurIPS 2023 Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin D. Haeffele, Yi Ma

Particularly, we show that the standard transformer block can be derived from alternating optimization on complementary parts of this objective: the multi-head self-attention operator can be viewed as a gradient descent step to compress the token sets by minimizing their lossy coding rate, and the subsequent multi-layer perceptron can be viewed as attempting to sparsify the representation of the tokens.

Representation Learning

Representation Learning via Manifold Flattening and Reconstruction

1 code implementation2 May 2023 Michael Psenka, Druv Pai, Vishal Raman, Shankar Sastry, Yi Ma

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold.

Data Compression Representation Learning

EMP-SSL: Towards Self-Supervised Learning in One Training Epoch

2 code implementations8 Apr 2023 Shengbang Tong, Yubei Chen, Yi Ma, Yann Lecun

Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation.

Quantization Self-Supervised Learning

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

2 code implementations NeurIPS 2023 Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine

Our approach, calibrated Q-learning (Cal-QL), accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale.

Offline RL Q-Learning +1

Closed-Loop Transcription via Convolutional Sparse Coding

no code implementations18 Feb 2023 Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung-Yeung Shum, Lionel M. Ni, Yi Ma

Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets.

Rolling Shutter Correction

Sherman-Morrison Regularization for ELAA Iterative Linear Precoding

no code implementations26 Jan 2023 Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli

The design of iterative linear precoding is recently challenged by extremely large aperture array (ELAA) systems, where conventional preconditioning techniques could hardly improve the channel condition.

Robot Subset Selection for Swarm Lifetime Maximization in Computation Offloading with Correlated Data Sources

no code implementations25 Jan 2023 Siqi Zhang, Na Yi, Yi Ma

When the number of subgraphs is maximized, the proposed subset selection approach is shown to be optimum in the AWGN channel.

Unsupervised Manifold Linearizing and Clustering

no code implementations ICCV 2023 Tianjiao Ding, Shengbang Tong, Kwan Ho Ryan Chan, Xili Dai, Yi Ma, Benjamin D. Haeffele

We consider the problem of simultaneously clustering and learning a linear representation of data lying close to a union of low-dimensional manifolds, a fundamental task in machine learning and computer vision.

Clustering Deep Clustering

Understanding the Complexity Gains of Single-Task RL with a Curriculum

no code implementations24 Dec 2022 Qiyang Li, Yuexiang Zhai, Yi Ma, Sergey Levine

Under mild regularity conditions on the curriculum, we show that sequentially solving each task in the multi-task RL problem is more computationally efficient than solving the original single-task problem, without any explicit exploration bonuses or other exploration strategies.

Reinforcement Learning (RL)

State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning

no code implementations28 Nov 2022 Chen Chen, Hongyao Tang, Yi Ma, Chao Wang, Qianli Shen, Dong Li, Jianye Hao

The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way.

Offline RL Q-Learning +2

Unsupervised Learning of Structured Representations via Closed-Loop Transcription

1 code implementation30 Oct 2022 Shengbang Tong, Xili Dai, Yubei Chen, Mingyang Li, Zengyi Li, Brent Yi, Yann Lecun, Yi Ma

This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes.

Revisiting Sparse Convolutional Model for Visual Recognition

1 code implementation24 Oct 2022 Xili Dai, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma

We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks.

Image Classification

Minimalistic Unsupervised Learning with the Sparse Manifold Transform

no code implementations30 Sep 2022 Yubei Chen, Zeyu Yun, Yi Ma, Bruno Olshausen, Yann Lecun

Though there remains a small performance gap between our simple constructive model and SOTA methods, the evidence points to this as a promising direction for achieving a principled and white-box approach to unsupervised learning.

Self-Supervised Learning Sparse Representation-based Classification +3

Power Allocation for FDMA-URLLC Downlink with Random Channel Assignment

no code implementations4 Aug 2022 Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli

With imperfect CSIT, the proposed approach can still provide remarkable user capacity at limited cost of transmit-power efficiency.

Constellation-Oriented Perturbation for Scalable-Complexity MIMO Nonlinear Precoding

no code implementations4 Aug 2022 Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli, Fei Tong

The basic concept of COP is to apply vector perturbation (VP) in the constellation domain instead of symbol domain; as often used in conventional techniques.

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

1 code implementation13 Jul 2022 Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan

Leveraging this observation, we propose a Train-Convexify-Train (TCT) procedure to sidestep this issue: first, learn features using off-the-shelf methods (e. g., FedAvg); then, optimize a convexified problem obtained from the network's empirical neural tangent kernel approximation.

Federated Learning

On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence

no code implementations11 Jul 2022 Yi Ma, Doris Tsao, Heung-Yeung Shum

Ten years into the revival of deep networks and artificial intelligence, we propose a theoretical framework that sheds light on understanding deep networks within a bigger picture of Intelligence in general.

Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games

1 code implementation18 Jun 2022 Druv Pai, Michael Psenka, Chih-Yuan Chiu, Manxi Wu, Edgar Dobriban, Yi Ma

We consider the problem of learning discriminative representations for data in a high-dimensional space with distribution supported on or around multiple low-dimensional linear subspaces.

Representation Learning

Robust Calibration with Multi-domain Temperature Scaling

no code implementations6 Jun 2022 Yaodong Yu, Stephen Bates, Yi Ma, Michael I. Jordan

Uncertainty quantification is essential for the reliable deployment of machine learning models to high-stakes application domains.

Uncertainty Quantification

PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

no code implementations6 Apr 2022 Tong Sang, Hongyao Tang, Yi Ma, Jianye Hao, Yan Zheng, Zhaopeng Meng, Boyan Li, Zhen Wang

In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF.

Contrastive Learning Decision Making

Efficient Maximal Coding Rate Reduction by Variational Forms

no code implementations CVPR 2022 Christina Baek, Ziyang Wu, Kwan Ho Ryan Chan, Tianjiao Ding, Yi Ma, Benjamin D. Haeffele

The principle of Maximal Coding Rate Reduction (MCR$^2$) has recently been proposed as a training objective for learning discriminative low-dimensional structures intrinsic to high-dimensional data to allow for more robust training than standard approaches, such as cross-entropy minimization.

Image Classification

Incremental Learning of Structured Memory via Closed-Loop Transcription

1 code implementation11 Feb 2022 Shengbang Tong, Xili Dai, Ziyang Wu, Mingyang Li, Brent Yi, Yi Ma

Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discriminative and generative purposes.

Incremental Learning

Predicting Out-of-Distribution Error with the Projection Norm

1 code implementation11 Feb 2022 Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt

Projection Norm first uses model predictions to pseudo-label test samples and then trains a new model on the pseudo-labels.

Pseudo Label text-classification +1

Network-ELAA Beamforming and Coverage Analysis for eMBB/URLLC in Spatially Non-Stationary Rician Channels

no code implementations19 Jan 2022 Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli, Fan Wang

Finally, it is shown that the network-ELAA can offer significant coverage extension (50% or more in most of cases) when comparing with the single-AP scenario.

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

no code implementations4 Jan 2022 Yi Ma, Yongqi Zhai, Ronggang Wang

In this paper, we propose the first learned fine-grained scalable image compression model (DeepFGS) to overcome the above two shortcomings.

Image Compression MS-SSIM +1

EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction

1 code implementation CVPR 2022 Xinyu Zhou, Peiqi Duan, Yi Ma, Boxin Shi

This paper proposes to use neuromorphic events for correcting rolling shutter (RS) images as consecutive global shutter (GS) frames.

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

no code implementations NeurIPS 2021 Yi Ma, Xiaotian Hao, Jianye Hao, Jiawen Lu, Xing Liu, Tong Xialiang, Mingxuan Yuan, Zhigang Li, Jie Tang, Zhaopeng Meng

To address this problem, existing methods partition the overall DPDP into fixed-size sub-problems by caching online generated orders and solve each sub-problem, or on this basis to utilize the predicted future orders to optimize each sub-problem further.

Hierarchical Reinforcement Learning

Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction

1 code implementation12 Nov 2021 Xili Dai, Shengbang Tong, Mingyang Li, Ziyang Wu, Michael Psenka, Kwan Ho Ryan Chan, Pengyuan Zhai, Yaodong Yu, Xiaojun Yuan, Heung Yeung Shum, Yi Ma

In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces.

PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction

1 code implementation3 Oct 2021 Yi Ma, Kong Aik Lee, Ville Hautamaki, Haizhou Li

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise.

Speaker Identification Speaker Verification +1

Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT

no code implementations3 Oct 2021 Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli, Zhibo Pang

In addition, a combinatorial approach of the MF beamforming and grouped space-time block code (G-STBC) is proposed to further mitigate the detrimental impact of the CSIT uncertainty.

Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning

1 code implementation8 Jul 2021 Yuexiang Zhai, Christina Baek, Zhengyuan Zhou, Jiantao Jiao, Yi Ma

In both OWSP and OWMP settings, we demonstrate that adding {\em intermediate rewards} to subgoals is more computationally efficient than only rewarding the agent once it completes the goal of reaching a terminal state.

Hierarchical Reinforcement Learning Q-Learning +1

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

no code implementations30 Jun 2021 Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield favorable convergence.

EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events

no code implementations CVPR 2021 Peiqi Duan, Zihao W. Wang, Xinyu Zhou, Yi Ma, Boxin Shi

EventZoom is trained in a noise-to-noise fashion where the two ends of the network are unfiltered noisy events, enforcing noise-free event restoration.

Denoising Image Reconstruction +1

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

1 code implementation18 Jun 2021 Jiabao Lei, Kui Jia, Yi Ma

More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface.

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

2 code implementations21 May 2021 Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

This work attempts to provide a plausible theoretical framework that aims to interpret modern deep (convolutional) networks from the principles of data compression and discriminative representation.

Data Compression

End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels

no code implementations4 May 2021 Songyan Xue, Yi Ma, Na Yi

In this paper, a novel end-to-end learning approach, namely JTRD-Net, is proposed for uplink multiuser single-input multiple-output (MU-SIMO) joint transmitter and non-coherent receiver design (JTRD) in fading channels.

Fully Convolutional Line Parsing

2 code implementations22 Apr 2021 Xili Dai, Haigang Gong, Shuai Wu, Xiaojun Yuan, Yi Ma

We conduct extensive experiments and show that our method achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU.

Line Segment Detection

NeRD: Neural 3D Reflection Symmetry Detector

2 code implementations CVPR 2021 Yichao Zhou, Shichen Liu, Yi Ma

Recent advances have shown that symmetry, a structural prior that most objects exhibit, can support a variety of single-view 3D understanding tasks.

Pose Estimation regression

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

1 code implementation16 Apr 2021 Cheng Yang, Jia Zheng, Xili Dai, Rui Tang, Yi Ma, Xiaojun Yuan

Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image.

Room Layout Estimation

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition

1 code implementation17 Mar 2021 Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma

To investigate this gap, we decompose the test risk into its bias and variance components and study their behavior as a function of adversarial training perturbation radii ($\varepsilon$).

Measuring GAN Training in Real Time

no code implementations1 Jan 2021 Yuexiang Zhai, Bai Jiang, Yi Ma, Hao Chen

Generative Adversarial Networks (GAN) are popular generative models of images.

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

no code implementations NeurIPS 2020 Chaobing Song, Zhengyuan Zhou, Yichao Zhou, Yong Jiang, Yi Ma

The optimization problems associated with training generative adversarial neural networks can be largely reduced to certain {\em non-monotone} variational inequality problems (VIPs), whereas existing convergence results are mostly based on monotone or strongly monotone assumptions.

Incremental Learning via Rate Reduction

no code implementations CVPR 2021 Ziyang Wu, Christina Baek, Chong You, Yi Ma

Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes.

Incremental Learning

Deep Networks from the Principle of Rate Reduction

3 code implementations27 Oct 2020 Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

The layered architectures, linear and nonlinear operators, and even parameters of the network are all explicitly constructed layer-by-layer in a forward propagation fashion by emulating the gradient scheme.

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients

1 code implementation28 Sep 2020 Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan YAO

Even replacing only the first layer of a ResNet by such a ODE block can exhibit further improvement in robustness, e. g., under PGD-20 ($\ell_\infty=0. 031$) attack on CIFAR-10 dataset, it achieves 91. 57\% and natural accuracy and 62. 35\% robust accuracy, while a counterpart architecture of ResNet trained with TRADES achieves natural and robust accuracy 76. 29\% and 45. 24\%, respectively.

Adversarial Defense Adversarial Robustness

LungRN+NL: An Improved Adventitious Lung Sound Classification Using Non-Local Block ResNet Neural Network with Mixup Data Augmentation

no code implementations Interspeech 2020 Yi Ma, Xinzi Xu, Yongfu Li

An adventitious lung sound classification model, LungRN+NL, is proposed in this work, which has demonstrated a drastic improvement compared to our previous work and the state-of-the-art models.

Audio Classification Data Augmentation +1

Deep Isometric Learning for Visual Recognition

1 code implementation ICML 2020 Haozhi Qi, Chong You, Xiaolong Wang, Yi Ma, Jitendra Malik

Initialization, normalization, and skip connections are believed to be three indispensable techniques for training very deep convolutional neural networks and obtaining state-of-the-art performance.

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

no code implementations NeurIPS 2020 Chaobing Song, Yong Jiang, Yi Ma

Meanwhile, VRADA matches the lower bound of the general convex setting up to a $\log\log n$ factor and matches the lower bounds in both regimes $n\le \Theta(\kappa)$ and $n\gg \kappa$ of the strongly convex setting, where $\kappa$ denotes the condition number.

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction

2 code implementations17 Jun 2020 Yichao Zhou, Shichen Liu, Yi Ma

In this work, we focus on object-level 3D reconstruction and present a geometry-based end-to-end deep learning framework that first detects the mirror plane of reflection symmetry that commonly exists in man-made objects and then predicts depth maps by finding the intra-image pixel-wise correspondence of the symmetry.

3D Reconstruction Single-View 3D Reconstruction

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

1 code implementation NeurIPS 2020 Chong You, Zhihui Zhu, Qing Qu, Yi Ma

This paper shows that with a double over-parameterization for both the low-rank matrix and sparse corruption, gradient descent with discrepant learning rates provably recovers the underlying matrix even without prior knowledge on neither rank of the matrix nor sparsity of the corruption.

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

2 code implementations NeurIPS 2020 Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma

To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class.

Clustering Contrastive Learning +1

Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising

no code implementations9 May 2020 Xiaotian Hao, Junqi Jin, Jianye Hao, Jin Li, Weixun Wang, Yi Ma, Zhenzhe Zheng, Han Li, Jian Xu, Kun Gai

Bipartite b-matching is fundamental in algorithm design, and has been widely applied into economic markets, labor markets, etc.

On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems

no code implementations14 Apr 2020 Songyan Xue, Yi Ma, Na Yi, Rahim Tafazolli

Otherwise, it is called non-systematic waveform, where no artificial design is involved.

A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection

no code implementations1 Apr 2020 Songyan Xue, Yi Ma, Na Yi, Terence E. Dodgson

Motivated by this finding, we propose a novel modular neural network based approach, termed MNNet, where the whole network is formed by a set of pre-defined ANN modules.

Quantization

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

1 code implementation ICML 2020 Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma

We provide a simple explanation for this by measuring the bias and variance of neural networks: while the bias is monotonically decreasing as in the classical theory, the variance is unimodal or bell-shaped: it increases then decreases with the width of the network.

KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge

no code implementations18 Feb 2020 Peng Zhang, Jianye Hao, Weixun Wang, Hongyao Tang, Yi Ma, Yihai Duan, Yan Zheng

Our framework consists of a fuzzy rule controller to represent human knowledge and a refine module to fine-tune suboptimal prior knowledge.

Common Sense Reasoning Continuous Control +2

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

1 code implementation NeurIPS 2019 Yichao Zhou, Haozhi Qi, Jingwei Huang, Yi Ma

We present a simple yet effective end-to-end trainable deep network with geometry-inspired convolutional operators for detecting vanishing points in images.

Camera Calibration

Spectral-based Graph Convolutional Network for Directed Graphs

no code implementations21 Jul 2019 Yi Ma, Jianye Hao, Yaodong Yang, Han Li, Junqi Jin, Guangyong Chen

Our approach can work directly on directed graph data in semi-supervised nodes classification tasks.

Complete Dictionary Learning via $\ell^4$-Norm Maximization over the Orthogonal Group

no code implementations6 Jun 2019 Yuexiang Zhai, Zitong Yang, Zhenyu Liao, John Wright, Yi Ma

Most existing methods solve the dictionary (and sparse representations) based on heuristic algorithms, usually without theoretical guarantees for either optimality or complexity.

Dictionary Learning

Unified Acceleration of High-Order Algorithms under Hölder Continuity and Uniform Convexity

no code implementations3 Jun 2019 Chaobing Song, Yong Jiang, Yi Ma

In this general convex setting, we propose a concise unified acceleration framework (UAF), which reconciles the two different high-order acceleration approaches, one by Nesterov and Baes [29, 3, 33] and one by Monteiro and Svaiter [25].

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

2 code implementations ICCV 2019 Yichao Zhou, Haozhi Qi, Yuexiang Zhai, Qi Sun, Zhili Chen, Li-Yi Wei, Yi Ma

In this paper, we propose a method to obtain a compact and accurate 3D wireframe representation from a single image by effectively exploiting global structural regularities.

End-to-End Wireframe Parsing

1 code implementation ICCV 2019 Yichao Zhou, Haozhi Qi, Yi Ma

We conduct extensive experiments and show that our method significantly outperforms the previous state-of-the-art wireframe and line extraction algorithms.

Line Segment Detection Wireframe Parsing

Fine-grained Video Categorization with Redundancy Reduction Attention

no code implementations ECCV 2018 Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma

Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.

Action Recognition Video Classification

Structured Attentions for Visual Question Answering

1 code implementation ICCV 2017 Chen Zhu, Yanpeng Zhao, Shuaiyi Huang, Kewei Tu, Yi Ma

In this paper, we demonstrate the importance of encoding such relations by showing the limited effective receptive field of ResNet on two datasets, and propose to model the visual attention as a multivariate distribution over a grid-structured Conditional Random Field on image regions.

Visual Question Answering

Graph Construction with Label Information for Semi-Supervised Learning

no code implementations8 Jul 2016 Liansheng Zhuang, Zihan Zhou, Jingwen Yin, Shenghua Gao, Zhouchen Lin, Yi Ma, Nenghai Yu

In the literature, most existing graph-based semi-supervised learning (SSL) methods only use the label information of observed samples in the label propagation stage, while ignoring such valuable information when learning the graph.

graph construction Graph Learning

Single-Image Crowd Counting via Multi-Column Convolutional Neural Network

5 code implementations Conference 2016 Yingying Zhang, Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma

To this end, we have proposed a simple but effective Multi-column Convolutional Neural Network (MCNN) architecture to map the image to its crowd density map.

Crowd Counting

Low-Rank Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image Denoising

no code implementations ICCV 2015 Weisheng Dong, Guangyu Li, Guangming Shi, Xin Li, Yi Ma

Patch-based low-rank models have shown effective in exploiting spatial redundancy of natural images especially for the application of image denoising.

Dictionary Learning Image Denoising

Automatic Layer Separation using Light Field Imaging

no code implementations15 Jun 2015 Qiaosong Wang, Haiting Lin, Yi Ma, Sing Bing Kang, Jingyi Yu

We propose a novel approach that jointly removes reflection or translucent layer from a scene and estimates scene depth.

Generalized Tensor Total Variation Minimization for Visual Data Recovery

no code implementations CVPR 2015 Xiaojie Guo, Yi Ma

In this paper, we propose a definition of Generalized Tensor Total Variation norm (GTV) that considers both the inhomogeneity and the multi-directionality of responses to derivative-like filters.

Denoising

Robust Face Recognition by Constrained Part-based Alignment

no code implementations20 Jan 2015 Yuting Zhang, Kui Jia, Yueming Wang, Gang Pan, Tsung-Han Chan, Yi Ma

By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression.

Face Alignment Face Recognition +1

Constructing a Non-Negative Low Rank and Sparse Graph with Data-Adaptive Features

no code implementations3 Sep 2014 Liansheng Zhuang, Shenghua Gao, Jinhui Tang, Jingjing Wang, Zhouchen Lin, Yi Ma

This paper aims at constructing a good graph for discovering intrinsic data structures in a semi-supervised learning setting.

graph construction

Robust Separation of Reflection from Multiple Images

no code implementations CVPR 2014 Xiaojie Guo, Xiaochun Cao, Yi Ma

When one records a video/image sequence through a transparent medium (e. g. glass), the image is often a superposition of a transmitted layer (scene behind the medium) and a reflected layer.

PCANet: A Simple Deep Learning Baseline for Image Classification?

2 code implementations14 Apr 2014 Tsung-Han Chan, Kui Jia, Shenghua Gao, Jiwen Lu, Zinan Zeng, Yi Ma

In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.

Classification Face Recognition +5

Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment

no code implementations8 Feb 2014 Liansheng Zhuang, Tsung-Han Chan, Allen Y. Yang, S. Shankar Sastry, Yi Ma

In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class.

Face Alignment Face Recognition +1

Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors

no code implementations NeurIPS 2013 Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma

In this context, the state-of-the-art algorithms RASL'' and "TILT'' can be viewed as two special cases of our work, and yet each only performs part of the function of our method."

Computational Efficiency

Plane-Based Content Preserving Warps for Video Stabilization

no code implementations CVPR 2013 Zihan Zhou, Hailin Jin, Yi Ma

Recently, a new image deformation technique called content-preserving warping (CPW) has been successfully employed to produce the state-of-the-art video stabilization results in many challenging cases.

Novel View Synthesis Video Stabilization

Learning by Associating Ambiguously Labeled Images

no code implementations CVPR 2013 Zinan Zeng, Shijie Xiao, Kui Jia, Tsung-Han Chan, Shenghua Gao, Dong Xu, Yi Ma

Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image.

Video Editing with Temporal, Spatial and Appearance Consistency

no code implementations CVPR 2013 Xiaojie Guo, Xiaochun Cao, Xiaowu Chen, Yi Ma

Given an area of interest in a video sequence, one may want to manipulate or edit the area, e. g. remove occlusions from or replace with an advertisement on it.

Image Matting Video Editing

Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer

no code implementations CVPR 2013 Liansheng Zhuang, Allen Y. Yang, Zihan Zhou, S. Shankar Sastry, Yi Ma

To compensate the missing illumination information typically provided by multiple training images, a sparse illumination transfer (SIT) technique is introduced.

Face Alignment Face Recognition +1

Blind Image Deblurring by Spectral Properties of Convolution Operators

no code implementations10 Sep 2012 Guangcan Liu, Shiyu Chang, Yi Ma

We show that the minimizer of this regularizer guarantees to give good approximation to the blur kernel if the original image is sharp enough.

Blind Image Deblurring Image Deblurring

Collaborative Representation based Classification for Face Recognition

no code implementations11 Apr 2012 Lei Zhang, Meng Yang, Xiangchu Feng, Yi Ma, David Zhang

It is widely believed that the l1- norm sparsity constraint on coding coefficients plays a key role in the success of SRC, while its use of all training samples to collaboratively represent the query sample is rather ignored.

Classification Face Recognition +3

Compressive Principal Component Pursuit

1 code implementation21 Feb 2012 John Wright, Arvind Ganesh, Kerui Min, Yi Ma

We consider the problem of recovering a target matrix that is a superposition of low-rank and sparse components, from a small set of linear measurements.

Information Theory Information Theory

Sparsity and Robustness in Face Recognition

no code implementations3 Nov 2011 John Wright, Arvind Ganesh, Allen Yang, Zihan Zhou, Yi Ma

This report concerns the use of techniques for sparse signal representation and sparse error correction for automatic face recognition.

Face Recognition Robust Face Recognition

The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices

no code implementations26 Sep 2010 Zhouchen Lin, Minming Chen, Yi Ma

This paper proposes scalable and fast algorithms for solving the Robust PCA problem, namely recovering a low-rank matrix with an unknown fraction of its entries being arbitrarily corrupted.

Optimization and Control Numerical Analysis Systems and Control

Fast L1-Minimization Algorithms For Robust Face Recognition

no code implementations21 Jul 2010 Allen Y. Yang, Zihan Zhou, Arvind Ganesh, S. Shankar Sastry, Yi Ma

L1-minimization refers to finding the minimum L1-norm solution to an underdetermined linear system b=Ax.

Compressive Sensing Face Recognition +1

Fast L1-Minimization Algorithms For Robust Face Recognition

1 code implementation21 Jul 2010 Allen Y. Yang, Zihan Zhou, Arvind Ganesh, S. Shankar Sastry, Yi Ma

L1-minimization refers to finding the minimum L1-norm solution to an underdetermined linear system b=Ax.

Compressive Sensing Face Recognition +1

Stable Principal Component Pursuit

1 code implementation14 Jan 2010 Zihan Zhou, XiaoDong Li, John Wright, Emmanuel Candes, Yi Ma

We further prove that the solution to a related convex program (a relaxed PCP) gives an estimate of the low-rank matrix that is simultaneously stable to small entrywise noise and robust to gross sparse errors.

Information Theory Information Theory

Robust Principal Component Analysis?

3 code implementations18 Dec 2009 Emmanuel J. Candes, Xiao-Dong Li, Yi Ma, John Wright

This suggests the possibility of a principled approach to robust principal component analysis since our methodology and results assert that one can recover the principal components of a data matrix even though a positive fraction of its entries are arbitrarily corrupted.

Information Theory Information Theory

Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization

no code implementations NeurIPS 2009 John Wright, Arvind Ganesh, Shankar Rao, Yigang Peng, Yi Ma

Principal component analysis is a fundamental operation in computational data analysis, with myriad applications ranging from web search to bioinformatics to computer vision and image analysis.

Cannot find the paper you are looking for? You can Submit a new open access paper.