b'Cihang Xie'

research

∙ 05/11/2023

An Inverse Scaling Law for CLIP Training

CLIP, the first foundation model that connects images and text, has enab...

0 Xianhang Li, et al. ∙

research

∙ 04/06/2023

Diffusion Models as Masked Autoencoders

There has been a longstanding belief that generation can facilitate a tr...

0 Chen Wei, et al. ∙

research

∙ 01/25/2023

On the Adversarial Robustness of Camera-based 3D Object Detection

In recent years, camera-based 3D object detection has gained widespread ...

0 Shaoyuan Xie, et al. ∙

research

∙ 12/20/2022

Unleashing the Power of Visual Prompting At the Pixel Level

This paper presents a simple and effective visual prompting method for a...

0 Junyang Wu, et al. ∙

research

∙ 12/01/2022

Localization vs. Semantics: How Can Language Benefit Visual Representation Learning?

Despite the superior performance brought by vision-and-language pretrain...

0 Zhuowan Li, et al. ∙

research

∙ 11/29/2022

Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

Modern deep neural networks tend to be evaluated on static test sets. On...

0 Nataniel Ruiz, et al. ∙

research

∙ 11/27/2022

Navigation as the Attacker Wishes? Towards Building Byzantine-Robust Embodied Agents under Federated Learning

Federated embodied agent learning protects the data privacy of individua...

0 Yunchao Zhang, et al. ∙

research

∙ 11/21/2022

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training

Video-language pre-training is crucial for learning powerful multi-modal...

0 Yuanze Lin, et al. ∙

research

∙ 09/06/2022

Bag of Tricks for FGSM Adversarial Training

Adversarial training (AT) with samples generated by Fast Gradient Sign M...

32 Zichao Li, et al. ∙

research

∙ 08/25/2022

Masked Autoencoders Enable Efficient Knowledge Distillers

This paper studies the potential of distilling knowledge from pre-traine...

55 Yutong Bai, et al. ∙

research

∙ 06/15/2022

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component f...

19 Sucheng Ren, et al. ∙

research

∙ 06/07/2022

Can CNNs Be More Robust Than Transformers?

The recent success of Vision Transformers is shaking the long dominance ...

82 Zeyu Wang, et al. ∙

research

∙ 05/24/2022

One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks

Unlearnable examples (ULEs) aim to protect data from unauthorized usage ...

0 Shutong Wu, et al. ∙

research

∙ 05/24/2022

Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks

The score-based query attacks (SQAs) pose practical threats to deep neur...

0 Sizhe Chen, et al. ∙

research

∙ 05/03/2022

In Defense of Image Pre-Training for Spatiotemporal Recognition

Image pre-training, the current de-facto paradigm for a wide range of vi...

6 Xianhang Li, et al. ∙

research

∙ 04/21/2022

Fast AdvProp

Adversarial Propagation (AdvProp) is an effective way to improve recogni...

3 Jieru Mei, et al. ∙

research

∙ 02/09/2022

Learning to Bootstrap for Combating Label Noise

Deep neural networks are powerful tools for representation learning, but...

14 Yuyin Zhou, et al. ∙

research

∙ 11/15/2021

iBOT: Image BERT Pre-Training with Online Tokenizer

The success of language Transformers is primarily attributed to the pret...

0 Jinghao Zhou, et al. ∙

research

∙ 11/10/2021

Are Transformers More Robust Than CNNs?

Transformer emerges as a powerful tool for visual recognition. In additi...

0 Yutong Bai, et al. ∙

research

∙ 10/01/2021

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

While neural symbolic methods demonstrate impressive performance in visu...

0 Zhuowan Li, et al. ∙

research

∙ 06/08/2021

Simulated Adversarial Testing of Face Recognition Models

Most machine learning models are validated and tested on fixed datasets....

0 Nataniel Ruiz, et al. ∙

research

∙ 03/23/2021

Robust and Accurate Object Detection via Adversarial Learning

Data augmentation has become a de facto component for training high-perf...

10 Xiangning Chen, et al. ∙

research

∙ 11/28/2020

Batch Normalization with Enhanced Linear Transformation

Batch normalization (BN) is a fundamental unit in modern deep networks, ...

15 Yuhui Xu, et al. ∙

research

∙ 10/12/2020

Shape-Texture Debiased Neural Network Training

Shape and texture are two prominent and complementary cues for recognizi...

21 Yingwei Li, et al. ∙

research

∙ 06/25/2020

Smooth Adversarial Training

It is commonly believed that networks cannot be both accurate and robust...

13 Cihang Xie, et al. ∙

research

∙ 04/12/2020

PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning

Patch-based attacks introduce a perceptible but localized change to the ...

6 Chenglin Yang, et al. ∙

research

∙ 04/04/2020

Neural Architecture Search for Lightweight Non-Local Networks

Non-Local (NL) blocks have been widely studied in various vision tasks. ...

5 Yingwei Li, et al. ∙

research

∙ 11/21/2019

Adversarial Examples Improve Image Recognition

Adversarial examples are commonly viewed as a threat to ConvNets. Here w...

24 Cihang Xie, et al. ∙

research

∙ 09/10/2019

UPC: Learning Universal Physical Camouflage Attacks on Object Detectors

In this paper, we study physical adversarial attacks on object detectors...

17 Lifeng Huang, et al. ∙

research

∙ 06/10/2019

Intriguing properties of adversarial training

Adversarial training is one of the main defenses against adversarial att...

0 Cihang Xie, et al. ∙

research

∙ 04/01/2019

Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses

This paper focuses on learning transferable adversarial examples specifi...

4 Yingwei Li, et al. ∙

research

∙ 12/09/2018

Learning Transferable Adversarial Examples via Ghost Networks

The recent development of adversarial attack has proven that ensemble-ba...

0 Yingwei Li, et al. ∙

research

∙ 12/09/2018

Feature Denoising for Improving Adversarial Robustness

Adversarial attacks to image classification systems present challenges t...

0 Cihang Xie, et al. ∙

research

∙ 03/31/2018

Adversarial Attacks and Defences Competition

To accelerate research on adversarial examples and robustness of machine...

0 Alexey Kurakin, et al. ∙

research

∙ 03/19/2018

Improving Transferability of Adversarial Examples with Input Diversity

Though convolutional neural networks have achieved state-of-the-art perf...

0 Cihang Xie, et al. ∙

research

∙ 12/01/2017

Single-Shot Object Detection with Enriched Semantics

We propose a novel single shot object detection network named Detection ...

0 Zhishuai Zhang, et al. ∙

research

∙ 11/13/2017

Visual Concepts and Compositional Voting

It is very attractive to formulate vision in terms of pattern theory Mum...

0 Jianyu Wang, et al. ∙

research

∙ 11/06/2017

Mitigating adversarial effects through randomization

Convolutional neural networks have demonstrated their powerful ability o...

0 Cihang Xie, et al. ∙

research

∙ 09/14/2017

DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion

In this paper, we study the task of detecting semantic parts of an objec...

0 Zhishuai Zhang, et al. ∙

research

∙ 07/25/2017

Detecting Semantic Parts on Partially Occluded Objects

In this paper, we address the task of detecting semantic parts on partia...

0 Jianyu Wang, et al. ∙

research

∙ 03/24/2017

Adversarial Examples for Semantic Segmentation and Object Detection

It has been well demonstrated that adversarial examples, i.e., natural i...

0 Cihang Xie, et al. ∙

Cihang Xie

Featured Co-authors