3.5k citations · 9.4k across the 54 of their papers we have counts for
10 papers · 2 filters
FACTS: First Amplify Correlations and Then Slice to Discover Bias
Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu +1
Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes (e.g. context). Models trained…
ICON: Reliably Benchmarking Predictive Inequity in Object Detection
Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky +1
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising. Ana…
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya +10
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effect…
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
Viraj Prabhu, Sriram Yenamandra, Prithvijit Chattopadhyay +1
We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE). Our method leverages recent progress in la…
ZipIt! Merging Models from Different Tasks without Training
George Stoica, Daniel Bolya, Jakob Bjorner +3
Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct m…
Benchmarking Low-Shot Robustness to Natural Distribution Shifts
Aaditya Singh, Kartik Sarangmath, Prithvijit Chattopadhyay +1
Robustness to natural distribution shifts has seen remarkable progress thanks to recent pre-training strategies combined with better fine-tuning methods. However, such fine-tuning…
Token Merging for Fast Stable Diffusion
Daniel Bolya, Judy Hoffman
The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. B…
Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
Arun V. Reddy, Ketul Shah, William Paul +6
Human action recognition is a challenging problem, particularly when there is high variability in factors such as subject appearance, backgrounds and viewpoint. While deep neural n…
Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
Viraj Prabhu, David Acuna, Andrew Liao +5
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domai…
Mitigating Bias in Visual Transformers via Targeted Alignment
Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar +1
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness…