activity
20182021
most citedEigen Analysis of Self-Attention and its Reconstruction from Partial Computation

5 citations · 12 across the 7 of their papers we have counts for

collaborators

17 papers

cs.CV20211 cited

PROVES: Establishing Image Provenance using Semantic Signatures

Mingyang Xie, Manav Kulshrestha, Shaojie Wang +4

Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results. However, one of the deleterious…

cs.LG2021

Leveraging redundancy in attention with Reuse Transformers

Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit +5

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications i…

cs.LG20215 cited

Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation

Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain +3

State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we inv…

cs.CV2021

Understanding Robustness of Transformers for Image Classification

Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner +3

Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (Vi…

cs.CV20201 cited

Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments

Zhihao Xia, Michaël Gharbi, Federico Perazzi +2

We introduce a neural network-based method to denoise pairs of images taken in quick succession, with and without a flash, in low-light environments. Our goal is to produce a high-…

cs.LG20202 cited

Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints

Ayan Chakrabarti, Roch Guérin, Chenyang Lu +1

To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded…