605 citations · 4k across the 143 of their papers we have counts for
34 papers · 1 filter
Universal Pyramid Adversarial Training for Improved ViT Performance
Ping-yeh Chiang, Yipin Zhou, Omid Poursaeed +4
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transfor…
Seeing in Words: Learning to Classify through Language Bottlenecks
Khalid Saifullah, Yuxin Wen, Jonas Geiping +2
Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct…
Universal Guidance for Diffusion Models
Arpit Bansal, Hong-Min Chu, Avi Schwarzschild +4
Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work…
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
Manli Shu, Weili Nie, De-An Huang +4
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on ha…
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Arpit Bansal, Eitan Borgnia, Hong-Min Chu +6
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative beh…
A Deep Dive into Dataset Imbalance and Bias in Face Identification
Valeriia Cherepanova, Steven Reich, Samuel Dooley +3
As the deployment of automated face recognition (FR) systems proliferates, bias in these systems is not just an academic question, but a matter of public concern. Media portrayals…
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Amin Ghiasi, Hamid Kazemi, Steven Reich +3
Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for ea…
Are Commercial Face Detection Models as Biased as Academic Models?
Samuel Dooley, George Z. Wei, Tom Goldstein +1
As facial recognition systems are deployed more widely, scholars and activists have studied their biases and harms. Audits are commonly used to accomplish this and compare the algo…
Active Learning at the ImageNet Scale
Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang +4
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this l…
A Frequency Perspective of Adversarial Robustness
Shishira R Maiya, Max Ehrlich, Vatsal Agarwal +3
Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the…
Comparing Human and Machine Bias in Face Recognition
Samuel Dooley, Ryan Downing, George Wei +10
Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceiv…
Towards Transferable Adversarial Attacks on Vision Transformers
Zhipeng Wei, Jingjing Chen, Micah Goldblum +3
Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fa…
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
Roman Levin, Manli Shu, Eitan Borgnia +3
Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and ana…
Long-Short Transformer: Efficient Transformers for Language and Vision
Chen Zhu, Wei Ping, Chaowei Xiao +4
Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolu…
The Intrinsic Dimension of Images and Its Impact on Learning
Phillip Pope, Chen Zhu, Ahmed Abdelkader +2
It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common…
THAT: Two Head Adversarial Training for Improving Robustness at Scale
Zuxuan Wu, Tom Goldstein, Larry S. Davis +1
Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Traini…
Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
Shivam Akhauri, Laura Zheng, Tom Goldstein +1
Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with u…
Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
Yu Shen, Laura Zheng, Manli Shu +3
For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments. These external and environ…
LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
Valeriia Cherepanova, Micah Goldblum, Harrison Foley +4
Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These…
Encoding Robustness to Image Style via Adversarial Feature Perturbations
Manli Shu, Zuxuan Wu, Micah Goldblum +1
Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are…
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Jonas Geiping, Liam Fowl, W. Ronny Huang +4
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification…
Detection as Regression: Certified Object Detection by Median Smoothing
Ping-yeh Chiang, Michael J. Curry, Ahmed Abdelkader +3
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image…
Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
Zuxuan Wu, Ser-Nam Lim, Larry Davis +1
We present a systematic study of adversarial attacks on state-of-the-art object detection frameworks. Using standard detection datasets, we train patterns that suppress the objectn…
ACE: Adapting to Changing Environments for Semantic Segmentation
Zuxuan Wu, Xin Wang, Joseph E. Gonzalez +2
Deep neural networks exhibit exceptional accuracy when they are trained and tested on the same data distributions. However, neural classifiers are often extremely brittle when conf…