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.
As a Ph.D. student, my work investigates how various types of noise—such as low-resolution, and environmental distortions—impact the performance of deep learning models, including transformers and vision-language models (VLMs).
Previously, my Master's thesis centered on Person Re-Identification (ReID) in surveillance settings, a domain inherently affected by low-resolution and noisy visual data.
|
|
Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
Priyank Pathak,
Yogesh S. Rawat,
ICCV, 2025
Paper /
Code
We propose a lightweight, annotation-free proxy for mitigating appearance bias in ReID models, when clothing annotations arent avaialble.
We propose Colors See, Colors Ignore (CSCI), a RGB-only method that leverages color information directly from raw images or video frames. CSCI efficiently captures colorrelated appearance bias (‘Color See’) while disentangling it from identity-relevant ReID features (‘Color Ignore’).
|
|
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
Paper /
Project Page /
Code
We introduce LR0.FM, a benchmark evaluating the impact of low resolution on the zero-shot classification performance of VLMs. We propose a novel metric, Weighted Aggregated Robustness, to address the limitations of existing metrics and LR-TK0, to enhance the robustness of models without compromising their pre-trained weights. We demonstrate the effectiveness of LR-TK0 for robustness against low-resolution across several datasets and its generalization capability across backbones and other approaches.
|
|
Video person re-id: Fantastic techniques and where to find them (student abstract)
Priyank Pathak,
Amir Erfan Eshratifar,
Michael Gormish,
AAAI, 2020
Paper /
Code
One of the first works to solve Person Reid exploring multiple techniques to improve accuracy on video ReID model.
|
|