Search Results for author:
Found 79 papers, 26 papers with code
Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships.
LIPT: Latency-aware Image Processing Transformer
Extensive experiments on multiple image processing tasks (e. g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR.
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model.
IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions
Recent advances have demonstrated the powerful capability of transformer architecture in image restoration.
Distilling Semantic Priors from SAM to Efficient Image Restoration Models
SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models.
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
Self-Supervised Representation Learning with Meta Comprehensive Regularization
Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features.
Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks
We study a family of distributed stochastic optimization algorithms where gradients are sampled by a token traversing a network of agents in random-walk fashion.
Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications
Two-timescale stochastic approximation (TTSA) is among the most general frameworks for iterative stochastic algorithms.
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature.
CBQ: Cross-Block Quantization for Large Language Models
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
GenDet: Towards Good Generalizations for AI-Generated Image Detection
The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news.
Massive Wireless Energy Transfer without Channel State Information via Imperfect Intelligent Reflecting Surfaces
Intelligent Reflecting Surface (IRS) utilizes low-cost, passive reflecting elements to enhance the passive beam gain, improve Wireless Energy Transfer (WET) efficiency, and enable its deployment for numerous Internet of Things (IoT) devices.
Learning-Based Biharmonic Augmentation for Point Cloud Classification
Point cloud datasets often suffer from inadequate sample sizes in comparison to image datasets, making data augmentation challenging.
Spatio-Temporal Meta Contrastive Learning
Although recent STGNN models with contrastive learning aim to address these challenges, most of them use pre-defined augmentation strategies that heavily depend on manual design and cannot be customized for different Spatio-Temporal Graph (STG) scenarios.
Green Beamforming Design for Integrated Sensing and Communication Systems: A Practical Approach Using Beam-Matching Error Metrics
In this paper, we propose a green beamforming design for the integrated sensing and communication (ISAC) system, using beam-matching error to assess radar performance.
Robust NOMA-assisted OTFS-ISAC Network Design with 3D Motion Prediction Topology
This paper proposes a novel non-orthogonal multiple access (NOMA)-assisted orthogonal time-frequency space (OTFS)-integrated sensing and communication (ISAC) network, which uses unmanned aerial vehicles (UAVs) as air base stations to support multiple users.
IFT: Image Fusion Transformer for Ghost-free High Dynamic Range Imaging
By matching similar patches between frames, objects with large motion ranges in dynamic scenes can be aligned, which can effectively alleviate the generation of artifacts.
Data Upcycling Knowledge Distillation for Image Super-Resolution
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models.
Ranked #22 on
Image Super-Resolution
on Urban100 - 4x upscaling
USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation
Rather than risk potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, we consider them as uncertainty regions, exempting them from pseudo-labeling and allowing the network to self-learn.
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited.
A Pre-trained Data Deduplication Model based on Active Learning
In the era of big data, the issue of data quality has become increasingly prominent.
Persistent Ballistic Entanglement Spreading with Optimal Control in Quantum Spin Chains
In this work, we uncover that the ``variational entanglement-enhancing'' field (VEEF) robustly induces a persistent ballistic spreading of entanglement in quantum spin chains.
Augmenting Greybox Fuzzing with Generative AI
Large language models (LLM) pre-trained with an enormous amount of natural language corpus have proved to be effective for understanding the implicit format syntax and generating format-conforming inputs.
Self-Repellent Random Walks on General Graphs -- Achieving Minimal Sampling Variance via Nonlinear Markov Chains
We consider random walks on discrete state spaces, such as general undirected graphs, where the random walkers are designed to approximate a target quantity over the network topology via sampling and neighborhood exploration in the form of Markov chain Monte Carlo (MCMC) procedures.
You Only Segment Once: Towards Real-Time Panoptic Segmentation
To reduce the computational overhead, we design a feature pyramid aggregator for the feature map extraction, and a separable dynamic decoder for the panoptic kernel generation.
Bag of Tricks with Quantized Convolutional Neural Networks for image classification
To bridge this gap, we collect and improve existing quantization methods and propose a gold guideline for post-training quantization.
Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation
Based on this SCM, we theoretically prove that the quality of generated images is positively correlated with the amount of feature information.
DistilPose: Tokenized Pose Regression with Heatmap Distillation
Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps.
Orthogonal-Time-Frequency-Space Signal Design for Integrated Data and Energy Transfer: Benefits from Doppler Offsets
Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components.
Toward Accurate Post-Training Quantization for Image Super Resolution
In this paper, we study post-training quantization(PTQ) for image super resolution using only a few unlabeled calibration images.
RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis
We present Reference-guided Super-Resolution Neural Radiance Field (RefSR-NeRF) that extends NeRF to super resolution and photorealistic novel view synthesis.
Elastic Aggregation for Federated Optimization
Federated learning enables the privacy-preserving training of neural network models using real-world data across distributed clients.
MSRA-SR: Image Super-resolution Transformer with Multi-scale Shared Representation Acquisition
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation.
SISO-OFDM and MISO-OFDM Counterparts for "Wideband Waveforming for Integrated Data and Energy Transfer: Creating Extra Gain Beyond Multiple Antennas and Multiple Carriers"
In this article, we proposethe SISO-OFDM and MISO-OFDM based IDET systems, which are the counterparts of our optimal wideband waveforming strategy in [1].
Prediction of superconducting properties of materials based on machine learning models
Based on this, this manuscript proposes the use of XGBoost model to identify superconductors; the first application of deep forest model to predict the critical temperature of superconductors; the first application of deep forest to predict the band gap of materials; and application of a new sub-network model to predict the Fermi energy level of materials.
Rethinking skip connection model as a learnable Markov chain
In this work, we deep dive into the model's behaviors with skip connections which can be formulated as a learnable Markov chain.
Efficiency Ordering of Stochastic Gradient Descent
We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i. i. d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense.
Bi-SIS Epidemics on Graphs -- Quantitative Analysis of Coexistence Equilibria
We consider a system in which two viruses of the Susceptible-Infected-Susceptible (SIS) type compete over general, overlaid graphs.
Deep Machine Learning Reconstructing Lattice Topology with Strong Thermal Fluctuations
In this work, we demonstrate the validity of the deep convolutional neural network (CNN) on reconstructing the lattice topology (i. e., spin connectivities) in the presence of strong thermal fluctuations and unbalanced data.
DRAformer: Differentially Reconstructed Attention Transformer for Time-Series Forecasting
Time-series forecasting plays an important role in many real-world scenarios, such as equipment life cycle forecasting, weather forecasting, and traffic flow forecasting.
Nearest Neighbor Classifier with Margin Penalty for Active Learning
As a result, informative samples in the margin area can not be discovered and AL performance are damaged.
Spatio-Temporal Latent Graph Structure Learning for Traffic Forecasting
Accurate traffic forecasting, the foundation of intelligent transportation systems (ITS), has never been more significant than nowadays due to the prosperity of smart cities and urban computing.
Elastic-Link for Binarized Neural Network
For example, we raise the top-1 accuracy of binarized ResNet26 from 57. 9% to 64. 0%.
Patent Data for Engineering Design: A Critical Review and Future Directions
Patent data have long been used for engineering design research because of its large and expanding size, and widely varying massive amount of design information contained in patents.
Domain-Invariant Representation Learning with Global and Local Consistency
In this paper, we give an analysis of the existing representation learning framework of unsupervised domain adaptation and show that the learned feature representations of the source domain samples are with discriminability, compressibility, and transferability.
GIR Framework: Learning Graph Positional Embeddings with Anchor Indication and Path Encoding
In this work, we propose a novel framework which follows the anchor-based idea and aims at conveying distance information implicitly along the MPNN message passing steps for encoding position information, node attributes, and graph structure in a more flexible way.
Prediction of properties of metal alloy materials based on machine learning
The experimental results show that the machine learning can predict the material properties accurately.
LODE: Deep Local Deblurring and A New Benchmark
While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake.
OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework
Federated Learning alleviates these problems by decentralizing model training, thereby removing the need for data transfer and aggregation.
Information Theory-Guided Heuristic Progressive Multi-View Coding
To this end, we rethink the existing multi-view learning paradigm from the information theoretical perspective and then propose a novel information theoretical framework for generalized multi-view learning.
Unifying Nonlocal Blocks for Neural Networks
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
Deep Learning for Technical Document Classification
In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and automated document classification.
Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling
The hybridizations of machine learning and quantum physics have caused essential impacts to the methodology in both fields.
Data-Driven Design-by-Analogy: State of the Art and Future Directions
Design-by-Analogy (DbA) is a design methodology wherein new solutions, opportunities or designs are generated in a target domain based on inspiration drawn from a source domain; it can benefit designers in mitigating design fixation and improving design ideation outcomes.
Graph Inference Representation: Learning Graph Positional Embeddings with Anchor Path Encoding
We show that GIRs get outperformed results in position-aware scenarios, and performances on typical GNNs could be improved by fusing GIR embeddings.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on
Instance Segmentation
on COCO test-dev
Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
To further improve scalable models on semi-supervised learning tasks, we propose Self-Label-Enhance (SLE) framework combining self-training approach and label propagation in depth.
Ranked #4 on
Node Property Prediction
on ogbn-papers100M
Learning the Superpixel in a Non-iterative and Lifelong Manner
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence.
Involution: Inverting the Inherence of Convolution for Visual Recognition
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision.
Ranked #706 on
Image Classification
on ImageNet
Image-to-image Translation via Hierarchical Style Disentanglement
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.
Disentanglement
Multimodal Unsupervised Image-To-Image Translation
+1
Adaptive Graph Diffusion Networks
Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications.
Robust Motion Averaging under Maximum Correntropy Criterion
Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem.
Architecture Disentanglement for Deep Neural Networks
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
A Convolutional Neural Network-based Patent Image Retrieval Method for Design Ideation
This approach is also illustrated in a case study of robot arm design retrieval.
Interpretable Machine Learning Model for Early Prediction of Mortality in Elderly Patients with Multiple Organ Dysfunction Syndrome (MODS): a Multicenter Retrospective Study and Cross Validation
This study aims to develop an interpretable and generalizable model for early mortality prediction in elderly patients with MODS.
Information Competing Process for Learning Diversified Representations
Learning representations with diversified information remains as an open problem.
Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
Especially, AGUIT benefits from two-fold: (1) It adopts a novel semi-supervised learning process by translating attributes of labeled data to unlabeled data, and then reconstructing the unlabeled data by a cycle consistency operation.
FluidC+: A novel community detection algorithm based on fluid propagation
In recent years, community detection has gradually become a hot topic in the complex network data mining field.
Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter
This paper focuses on robotic picking tasks in cluttered scenario.
Combining RGB and Points to Predict Grasping Region for Robotic Bin-Picking
This paper focuses on a robotic picking tasks in cluttered scenario.
Towards Visual Feature Translation
In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different visual search systems.
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.
An In-field Automatic Wheat Disease Diagnosis System
Crop diseases are responsible for the major production reduction and economic losses in agricultural industry world- wide.
Squeeze-and-Excitation Networks
Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2. 251%, surpassing the winning entry of 2016 by a relative improvement of ~25%.
Ranked #59 on
Image Classification
on CIFAR-10
A DNN Framework For Text Image Rectification From Planar Transformations
In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions.
A Key Volume Mining Deep Framework for Action Recognition
Training with a large proportion of irrelevant volumes will hurt performance.
