Search Results for author: Weizhong Zhang

Found 27 papers, 13 papers with code

PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering

1 code implementation8 Mar 2024 Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin

This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process.

Out-of-Distribution Detection using Neural Activation Prior

no code implementations28 Feb 2024 Weilin Wan, Weizhong Zhang, Cheng Jin

Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample.

Out-of-Distribution Detection

Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection

1 code implementation19 Dec 2023 Kaiyi Zhang, Yang Chen, Ximing Yang, Weizhong Zhang, Cheng Jin

Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint.

Disentanglement Point Cloud Generation

High-fidelity Person-centric Subject-to-Image Synthesis

1 code implementation17 Nov 2023 Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin

Specifically, we first develop two specialized pre-trained diffusion models, i. e., Text-driven Diffusion Model (TDM) and Subject-augmented Diffusion Model (SDM), for scene and person generation, respectively.

Image Generation Scene Generation

Spurious Feature Diversification Improves Out-of-distribution Generalization

no code implementations29 Sep 2023 Yong Lin, Lu Tan, Yifan Hao, Honam Wong, Hanze Dong, Weizhong Zhang, Yujiu Yang, Tong Zhang

Contrary to the conventional wisdom that focuses on learning invariant features for better OOD performance, our findings suggest that incorporating a large number of diverse spurious features weakens their individual contributions, leading to improved overall OOD generalization performance.

Out-of-Distribution Generalization

Test-Time Compensated Representation Learning for Extreme Traffic Forecasting

no code implementations16 Sep 2023 Zhiwei Zhang, Weizhong Zhang, Yaowei Huang, Kani Chen

In this paper, we identify an underexplored problem in multivariate traffic series prediction: extreme events.

Representation Learning

Probabilistic Bilevel Coreset Selection

no code implementations24 Jan 2023 Xiao Zhou, Renjie Pi, Weizhong Zhang, Yong Lin, Tong Zhang

The goal of coreset selection in supervised learning is to produce a weighted subset of data, so that training only on the subset achieves similar performance as training on the entire dataset.

Bilevel Optimization Continual Learning

Model Agnostic Sample Reweighting for Out-of-Distribution Learning

1 code implementation24 Jan 2023 Xiao Zhou, Yong Lin, Renjie Pi, Weizhong Zhang, Renzhe Xu, Peng Cui, Tong Zhang

The overfitting issue is addressed by considering a bilevel formulation to search for the sample reweighting, in which the generalization complexity depends on the search space of sample weights instead of the model size.

Normalizing Flow with Variational Latent Representation

1 code implementation21 Nov 2022 Hanze Dong, Shizhe Diao, Weizhong Zhang, Tong Zhang

The resulting method is significantly more powerful than the standard normalization flow approach for generating data distributions with multiple modes.

Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimization

no code implementations10 Nov 2022 Yueqi Xie, Weizhong Zhang, Renjie Pi, Fangzhao Wu, Qifeng Chen, Xing Xie, Sunghun Kim

Since at each round, the number of tunable parameters optimized on the server side equals the number of participating clients (thus independent of the model size), we are able to train a global model with massive parameters using only a small amount of proxy data (e. g., around one hundred samples).

Federated Learning

Fast Adversarial Training with Adaptive Step Size

no code implementations6 Jun 2022 Zhichao Huang, Yanbo Fan, Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.

Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning

2 code implementations25 May 2022 Jiahui Gao, Renjie Pi, Yong Lin, Hang Xu, Jiacheng Ye, Zhiyong Wu, Weizhong Zhang, Xiaodan Liang, Zhenguo Li, Lingpeng Kong

In this paradigm, the synthesized data from the PLM acts as the carrier of knowledge, which is used to train a task-specific model with orders of magnitude fewer parameters than the PLM, achieving both higher performance and efficiency than prompt-based zero-shot learning methods on PLMs.

text-classification Text Classification +1

Finding Dynamics Preserving Adversarial Winning Tickets

no code implementations14 Feb 2022 Xupeng Shi, Pengfei Zheng, A. Adam Ding, Yuan Gao, Weizhong Zhang

Modern deep neural networks (DNNs) are vulnerable to adversarial attacks and adversarial training has been shown to be a promising method for improving the adversarial robustness of DNNs.

Adversarial Robustness

Safe Screening for Sparse Conditional Random Fields

no code implementations27 Nov 2021 Weizhong Zhang, Shuang Qiu

To the best of our knowledge, this is the first screening method which introduces the dual optimum estimation technique -- by carefully exploring and exploiting the strong convexity and the complex structure of the dual problem -- in static screening methods to dynamic screening.

Structured Prediction

Efficient Neural Network Training via Forward and Backward Propagation Sparsification

1 code implementation NeurIPS 2021 Xiao Zhou, Weizhong Zhang, Zonghao Chen, Shizhe Diao, Tong Zhang

For the latter step, instead of using the chain rule based gradient estimators as in existing methods, we propose a variance reduced policy gradient estimator, which only requires two forward passes without backward propagation, thus achieving completely sparse training.

Efficient Neural Network

A Structure Feature Algorithm for Multi-modal Forearm Registration

no code implementations10 Nov 2021 Jiaxin Li, Yan Ding, Weizhong Zhang, Yifan Zhao, Lingxi Guo, Zhe Yang

Augmented reality technology based on image registration is becoming increasingly popular for the convenience of pre-surgery preparation and medical education.

Image Registration

Effective Sparsification of Neural Networks with Global Sparsity Constraint

1 code implementation CVPR 2021 Xiao Zhou, Weizhong Zhang, Hang Xu, Tong Zhang

Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments.

Network Pruning

Effective Training of Sparse Neural Networks under Global Sparsity Constraint

no code implementations1 Jan 2021 Xiao Zhou, Weizhong Zhang, Tong Zhang

An appealing feature of ProbMask is that the amounts of weight redundancy can be learned automatically via our constraint and thus we avoid the problem of tuning pruning rates individually for different layers in a network.

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

1 code implementation NeurIPS 2020 Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang

With the help of a new technique called {\it neural network grafting}, we demonstrate that even during the entire training process, feature distributions of differently initialized networks remain similar at each layer.

Convex Formulation of Overparameterized Deep Neural Networks

no code implementations18 Nov 2019 Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang

This new analysis is consistent with empirical observations that deep neural networks are capable of learning efficient feature representations.

A Sufficient Condition for Convergences of Adam and RMSProp

no code implementations CVPR 2019 Fangyu Zou, Li Shen, Zequn Jie, Weizhong Zhang, Wei Liu

Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples.

Stochastic Optimization

Safe Element Screening for Submodular Function Minimization

no code implementations ICML 2018 Weizhong Zhang, Bin Hong, Lin Ma, Wei Liu, Tong Zhang

Relying on this study, we subsequently propose a novel safe screening method to quickly identify the elements guaranteed to be included (we refer to them as active) or excluded (inactive) in the final optimal solution of SFM during the optimization process.

Combinatorial Optimization Sparse Learning

Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction

1 code implementation ICML 2017 Weizhong Zhang, Bin Hong, Wei Liu, Jieping Ye, Deng Cai, Xiaofei He, Jie Wang

By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.

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