146 citations · 562 across the 32 of their papers we have counts for
36 papers
MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Sadeep Jayasumana, Daniel Glasner, Srikumar Ramalingam +3
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computa…
Substance or Style: What Does Your Image Embedding Know?
Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng +5
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddin…
Benchmarking Robustness to Adversarial Image Obfuscations
Florian Stimberg, Ayan Chakrabarti, Chun-Ta Lu +9
Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfor…
Adaptive Edge Offloading for Image Classification Under Rate Limit
Jiaming Qiu, Ruiqi Wang, Ayan Chakrabarti +2
This paper considers a setting where embedded devices are used to acquire and classify images. Because of limited computing capacity, embedded devices rely on a parsimonious classi…
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…
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…
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…
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…
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-…
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…
Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositing
Jinghan Yang, Adith Boloor, Ayan Chakrabarti +2
There is considerable evidence that deep neural networks are vulnerable to adversarial perturbations applied directly to their digital inputs. However, it remains an open question…
Adversarial Robustness of Deep Sensor Fusion Models
Shaojie Wang, Tong Wu, Ayan Chakrabarti +1
We experimentally study the robustness of deep camera-LiDAR fusion architectures for 2D object detection in autonomous driving. First, we find that the fusion model is usually both…
Towards a MEMS-based Adaptive LIDAR
Francesco Pittaluga, Zaid Tasneem, Justin Folden +3
We present a proof-of-concept LIDAR design that allows adaptive real-time measurements according to dynamically specified measurement patterns. We describe our optical setup and ca…
Protecting Geolocation Privacy of Photo Collections
Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik
People increasingly share personal information, including their photos and photo collections, on social media. This information, however, can compromise individual privacy, particu…
Basis Prediction Networks for Effective Burst Denoising with Large Kernels
Zhihao Xia, Federico Perazzi, Michaël Gharbi +2
Bursts of images exhibit significant self-similarity across both time and space. This motivates a representation of the kernels as linear combinations of a small set of basis eleme…
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Weidong Cao, Liu Ke, Ayan Chakrabarti +1
Recent works propose neural network- (NN-) inspired analog-to-digital converters (NNADCs) and demonstrate their great potentials in many emerging applications. These NNADCs often r…
Training Image Estimators without Image Ground-Truth
Zhihao Xia, Ayan Chakrabarti
Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurr…
Generating and Exploiting Probabilistic Monocular Depth Estimates
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
Beyond depth estimation from a single image, the monocular cue is useful in a broader range of depth inference applications and settings---such as when one can leverage other avail…
Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures
Kyle Yee, Ayan Chakrabarti
Modern neural network-based algorithms are able to produce highly accurate depth estimates from stereo image pairs, nearly matching the reliability of measurements from more expens…
Backprop with Approximate Activations for Memory-efficient Network Training
Ayan Chakrabarti, Benjamin Moseley
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern w…
Learning to Separate Multiple Illuminants in a Single Image
Zhuo Hui, Ayan Chakrabarti, Kalyan Sunkavalli +1
We present a method to separate a single image captured under two illuminants, with different spectra, into the two images corresponding to the appearance of the scene under each i…
Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
Zhihao Xia, Ayan Chakrabarti
Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for mo…
Learning Privacy Preserving Encodings through Adversarial Training
Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information.…
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
Charles Schaff, David Yunis, Ayan Chakrabarti +1
The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment. In an increasing numb…