Search Results for author: Zhuang Liu

Found 51 papers, 33 papers with code

Test-Time Training for Generalization under Distribution Shifts

no code implementations ICML 2020 Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei Efros, University of California Moritz Hardt

We introduce a general approach, called test-time training, for improving the performance of predictive models when training and test data come from different distributions.

Image Classification Self-Supervised Learning

A Decade's Battle on Dataset Bias: Are We There Yet?

1 code implementation13 Mar 2024 Zhuang Liu, Kaiming He

We revisit the "dataset classification" experiment suggested by Torralba and Efros a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures.

Memorization

A Review of Data Mining in Personalized Education: Current Trends and Future Prospects

no code implementations27 Feb 2024 Zhang Xiong, Haoxuan Li, Zhuang Liu, Zhuofan Chen, Hao Zhou, Wenge Rong, Yuanxin Ouyang

Personalized education, tailored to individual student needs, leverages educational technology and artificial intelligence (AI) in the digital age to enhance learning effectiveness.

cognitive diagnosis Knowledge Tracing

Massive Activations in Large Language Models

1 code implementation27 Feb 2024 MingJie Sun, Xinlei Chen, J. Zico Kolter, Zhuang Liu

We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e. g., 100, 000 times larger).

Neural Network Diffusion

1 code implementation20 Feb 2024 Kai Wang, Zhaopan Xu, Yukun Zhou, Zelin Zang, Trevor Darrell, Zhuang Liu, Yang You

The autoencoder extracts latent representations of a subset of the trained network parameters.

Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization

1 code implementation3 Feb 2024 Bo Yang, Chen Wang, Xiaoshuang Ma, Beiping Song, Zhuang Liu

To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update.

Cross-Modal Retrieval Image Retrieval +2

Deconstructing Denoising Diffusion Models for Self-Supervised Learning

1 code implementation25 Jan 2024 Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming He

In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation.

Denoising Image Generation +3

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

Initializing Models with Larger Ones

1 code implementation30 Nov 2023 Zhiqiu Xu, Yanjie Chen, Kirill Vishniakov, Yida Yin, Zhiqiang Shen, Trevor Darrell, Lingjie Liu, Zhuang Liu

Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era.

Knowledge Distillation

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

1 code implementation15 Nov 2023 Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu

Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging.

Classification Robust classification +2

A Coefficient Makes SVRG Effective

1 code implementation9 Nov 2023 Yida Yin, Zhiqiu Xu, Zhiyuan Li, Trevor Darrell, Zhuang Liu

Stochastic Variance Reduced Gradient (SVRG), introduced by Johnson & Zhang (2013), is a theoretically compelling optimization method.

Image Classification

Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition

no code implementations21 Aug 2023 Zhuang Liu, Ye Yuan, Zhilong Ji, Jingfeng Bai, Xiang Bai

Then we design a semantic aware module (SAM), which projects the visual and classification feature into semantic space.

Graph Representation Learning

A Simple and Effective Pruning Approach for Large Language Models

2 code implementations20 Jun 2023 MingJie Sun, Zhuang Liu, Anna Bair, J. Zico Kolter

Motivated by the recent observation of emergent large magnitude features in LLMs, our approach prunes weights with the smallest magnitudes multiplied by the corresponding input activations, on a per-output basis.

Network Pruning

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning

1 code implementation13 Jun 2023 Arnav Chavan, Zhuang Liu, Deepak Gupta, Eric Xing, Zhiqiang Shen

We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks.

Domain Generalization Few-Shot Learning +1

ImageBind: One Embedding Space To Bind Them All

1 code implementation CVPR 2023 Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together.

Cross-Modal Retrieval Retrieval +7

A optimization framework for herbal prescription planning based on deep reinforcement learning

no code implementations25 Apr 2023 Kuo Yang, Zecong Yu, Xin Su, Xiong He, Ning Wang, Qiguang Zheng, Feidie Yu, Zhuang Liu, Tiancai Wen, Xuezhong Zhou

We constructed a high-quality benchmark dataset for sequential diagnosis and treatment of diabetes and evaluated PrescDRL against this benchmark.

reinforcement-learning Sequential Diagnosis

Dropout Reduces Underfitting

1 code implementation2 Mar 2023 Zhuang Liu, Zhiqiu Xu, Joseph Jin, Zhiqiang Shen, Trevor Darrell

Additionally, we explore a symmetric technique for regularizing overfitting models - late dropout, where dropout is not used in the early iterations and is only activated later in training.

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

10 code implementations CVPR 2023 Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie

This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation.

Object Detection Representation Learning +2

1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION

no code implementations30 Oct 2022 Zhuang Liu, Zhichao Zhao, Ye Yuan, Zhi Qiao, Jinfeng Bai, Zhilong Ji

In this technical report, we briefly introduce the solution of our team ''summer'' for Atomospheric Turbulence Mitigation in UG$^2$+ Challenge in CVPR 2022.

Image Quality Assessment Image Reconstruction

A ConvNet for the 2020s

45 code implementations CVPR 2022 Zhuang Liu, Hanzi Mao, Chao-yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie

The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model.

Classification Domain Generalization +3

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

1 code implementation CVPR 2022 Arnav Chavan, Zhiqiang Shen, Zhuang Liu, Zechun Liu, Kwang-Ting Cheng, Eric Xing

This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework.

MSeg: A Composite Dataset for Multi-domain Semantic Segmentation

2 code implementations CVPR 2020 John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun

We adopt zero-shot cross-dataset transfer as a benchmark to systematically evaluate a model's robustness and show that MSeg training yields substantially more robust models in comparison to training on individual datasets or naive mixing of datasets without the presented contributions.

Computational Efficiency Instance Segmentation +3

Contrastive Learning for Recommender System

no code implementations5 Jan 2021 Zhuang Liu, Yunpu Ma, Yuanxin Ouyang, Zhang Xiong

To solve this problem, we propose a graph contrastive learning module for a general recommender system that learns the embeddings in a self-supervised manner and reduces the randomness of message dropout.

Collaborative Filtering Contrastive Learning +2

Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control

1 code implementation ICLR 2021 Zhuang Liu, Xuanlin Li, Bingyi Kang, Trevor Darrell

In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms on continuous control tasks.

Continuous Control

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning

10 code implementations ICCV 2021 Yinbo Chen, Zhuang Liu, Huijuan Xu, Trevor Darrell, Xiaolong Wang

The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear.

Few-Shot Learning General Classification

Convolutional Networks with Dense Connectivity

no code implementations8 Jan 2020 Gao Huang, Zhuang Liu, Geoff Pleiss, Laurens van der Maaten, Kilian Q. Weinberger

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.

Object Recognition

Leveraging Prior Knowledge for Protein-Protein Interaction Extraction with Memory Network

no code implementations7 Jan 2020 Huiwei Zhou, Zhuang Liu, Shixian Ning, Yunlong Yang, Chengkun Lang, Yingyu Lin, Kun Ma

Automatically extracting Protein-Protein Interactions (PPI) from biomedical literature provides additional support for precision medicine efforts.

Entity Embeddings

Combining Context and Knowledge Representations for Chemical-Disease Relation Extraction

no code implementations23 Dec 2019 Huiwei Zhou, Yunlong Yang, Shixian Ning, Zhuang Liu, Chengkun Lang, Yingyu Lin, Degen Huang

KBs contain huge amounts of structured information about entities and relationships, therefore plays a pivotal role in chemical-disease relation (CDR) extraction.

Relation Relation Extraction

Knowledge-guided Convolutional Networks for Chemical-Disease Relation Extraction

no code implementations23 Dec 2019 Huiwei Zhou, Chengkun Lang, Zhuang Liu, Shixian Ning, Yingyu Lin, Lei Du

Results: This paper proposes a novel model called "Knowledge-guided Convolutional Networks (KCN)" to leverage prior knowledge for CDR extraction.

Entity Embeddings Relation +1

Improving Neural Protein-Protein Interaction Extraction with Knowledge Selection

no code implementations11 Dec 2019 Huiwei Zhou, Xuefei Li, Weihong Yao, Zhuang Liu, Shixian Ning, Chengkun Lang, Lei Du

Finally, the selected relation embedding and the context features are concatenated for PPI extraction.

Relation

Exploring Simple and Transferable Recognition-Aware Image Processing

1 code implementation21 Oct 2019 Zhuang Liu, Hung-Ju Wang, Tinghui Zhou, Zhiqiang Shen, Bingyi Kang, Evan Shelhamer, Trevor Darrell

Interestingly, the processing model's ability to enhance recognition quality can transfer when evaluated on models of different architectures, recognized categories, tasks and training datasets.

Image Retrieval Recommendation Systems

Regularization Matters in Policy Optimization

2 code implementations21 Oct 2019 Zhuang Liu, Xuanlin Li, Bingyi Kang, Trevor Darrell

In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms on continuous control tasks.

Continuous Control Reinforcement Learning (RL)

Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

3 code implementations29 Sep 2019 Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions.

Building change detection for remote sensing images CARLA MAP Leaderboard +6

Test-Time Training for Out-of-Distribution Generalization

no code implementations25 Sep 2019 Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt

We introduce a general approach, called test-time training, for improving the performance of predictive models when test and training data come from different distributions.

Image Classification Out-of-Distribution Generalization +1

DUT-BIM at MEDIQA 2019: Utilizing Transformer Network and Medical Domain-Specific Contextualized Representations for Question Answering

no code implementations WS 2019 Huiwei Zhou, Bizun Lei, Zhe Liu, Zhuang Liu

BioNLP 2019 proposes Question Answering (QA) task, which encourages the use of text mining technology to automatically judge whether a search result is an answer to the medical question.

Question Answering Relation

Few Sample Knowledge Distillation for Efficient Network Compression

1 code implementation CVPR 2020 Tianhong Li, Jianguo Li, Zhuang Liu, Chang-Shui Zhang

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high.

Knowledge Distillation Network Pruning +2

Few-shot Object Detection via Feature Reweighting

4 code implementations ICCV 2019 Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell

The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.

Few-Shot Learning Few-Shot Object Detection +3

Rethinking the Value of Network Pruning

2 code implementations ICLR 2019 Zhuang Liu, Ming-Jie Sun, Tinghui Zhou, Gao Huang, Trevor Darrell

Our observations are consistent for multiple network architectures, datasets, and tasks, which imply that: 1) training a large, over-parameterized model is often not necessary to obtain an efficient final model, 2) learned "important" weights of the large model are typically not useful for the small pruned model, 3) the pruned architecture itself, rather than a set of inherited "important" weights, is more crucial to the efficiency in the final model, which suggests that in some cases pruning can be useful as an architecture search paradigm.

Network Pruning Neural Architecture Search

Knowledge Distillation from Few Samples

no code implementations27 Sep 2018 Tianhong Li, Jianguo Li, Zhuang Liu, ChangShui Zhang

Taking the assumption that both "teacher" and "student" have the same feature map sizes at each corresponding block, we add a $1\times 1$ conv-layer at the end of each block in the student-net, and align the block-level outputs between "teacher" and "student" by estimating the parameters of the added layer with limited samples.

Knowledge Distillation

Object Detection from Scratch with Deep Supervision

1 code implementation25 Sep 2018 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.

General Classification Object +2

DSOD: Learning Deeply Supervised Object Detectors from Scratch

4 code implementations ICCV 2017 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.

General Classification Object +2

Snapshot Ensembles: Train 1, get M for free

10 code implementations1 Apr 2017 Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, Kilian Q. Weinberger

In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost.

Densely Connected Convolutional Networks

143 code implementations CVPR 2017 Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.

Breast Tumour Classification Crowd Counting +8

Deep Networks with Stochastic Depth

17 code implementations30 Mar 2016 Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger

With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4. 91% on CIFAR-10).

Image Classification

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