20 citations · 55 across the 17 of their papers we have counts for
5 papers · 1 filter
Caption supervision enables robust learners
Benjamin Feuer, Ameya Joshi, Chinmay Hegde
Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the…
Revisiting Self-Distillation
Minh Pham, Minsu Cho, Ameya Joshi +1
Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model c…
A Meta-Analysis of Distributionally-Robust Models
Benjamin Feuer, Ameya Joshi, Chinmay Hegde
State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts…
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Ameya Joshi, Minh Pham, Minsu Cho +4
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require aug…
Selective Network Linearization for Efficient Private Inference
Minsu Cho, Ameya Joshi, Siddharth Garg +2
Private inference (PI) enables inference directly on cryptographically secure data.While promising to address many privacy issues, it has seen limited use due to extreme runtimes.…