Research
My research focuses on developing efficient training techniques for computer vision models, with a particular emphasis on understanding the adverse effect of noise and enhancing the robustness of deep learning architectures in real-world scenarios.
My work investigates how various types of noise—such as low-resolution and environmental distortions (fog, rain, snow, etc.) impact the performance of deep learning models, including transformers and vision-language models (VLMs), in zero-shot setting.
On the side, I have extensive experience in Person Re-Identification (ReID) (also, my Master's thesis) centered on real-world CCTV cameras, a domain inherently affected by low-resolution and noisy visual data.
|
|
LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models
Priyank Pathak,
Shyam Marjit,
Shruti Vyas,
Yogesh S. Rawat,
ICLR, 2025 || ICCV (Non-Proceedings), 2025
Paper /
Project Page /
Code /
Arxiv
LR0.FM benchmark evaluates the impact of low resolution on the zero-shot performance of VLMs, via novel Weighted Aggregated Robustness metric.
LR-TK0 enhances the robustness of VLMs against low-resolution across several datasets without compromising their pre-trained weights.
|
|
Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
Priyank Pathak,
Yogesh S. Rawat,
ICCV, 2025
Paper /
Project Page /
Code /
Arxiv
Lightweight, annotation-free proxy for mitigating appearance bias in ReID models, when "expensive" clothing annotations aren't available.
Colors See, Colors Ignore (CSCI), an efficient RGB-only method leverages color information directly from raw images or video frames.
|
|
Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReID
Priyank Pathak,
Yogesh S. Rawat,
BMVC, 2025
Code /
Arxiv
We introduce Robustness against Low-Quality (RLQ) in clothes changing real-world ReID to make the model robust against low-quality artifacts like pixelation, out-of-focus blur, and motion blur.
|
|
Video person re-id: Fantastic techniques and where to find them (student abstract)
Priyank Pathak,
Amir Erfan Eshratifar,
Michael Gormish,
AAAI, 2020
Paper /
Code /
Arxiv
One of the first works in Person Reid exploring multiple techniques to improve accuracy on the Video ReID model, and proposing novel attention loss for helping model focus on certain frames more than the other.
|
|
Peeling Layers of Zero-Shot Object Detection for Robustness
Priyank Pathak,
Mukilan Karuppasamy*,
Aaditya Baranwal,
3 more authors
* equal contribution
Under Review
Removing bells and whistles of SOTA Zero-Shot Object Detectors under resolution degradation (`pixelation'), exposing 1) Vunerability of "backbones", 2) Certain images are immune to degradation 3) Minimal impact of "lanugage".
|
|
Incremental Scene Graph Updates in VLMs
Shresth Grover,
Priyank Pathak,
Akash Kumar,
Vibhav Vineet,
Yogesh S Rawat
Under Review
CosPlan benchmarks evaluates VLMs on "error-prone" sequence completion tasks, testing abilities like Error Detection and Sequence Completion ability.
Novel SGI, incrementally updates Scene Graphs better handle decision making.
|
|
Research Assistant, National University of Singapore
Singapore, Internship
Aug'22 - Dec'2022
|
|
Research Engineer, Amobee
New York (Remote), Full-time
June'20 - Aug'2021
|
|
Deep Learning Research Intern, Clarifai,
San Francisco (California), Internship
May'19 - Sept'19
|
|
Deep Learning Research Intern, Rice University,
Houston (Texas), Internship
May'17 - Aug'17
|
"Aloo has no plaace in Biryani" - Every Desi Foodie
Built upon Jon Barron's
template, and modified upon Rohit Gupta
|
|