Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
news
Icse_news
Published:
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Mmd-reid: A simple but effective solution for visible-thermal person reid
Published in The 32nd British Machine Vision Conference (BMVC), 2021
This paper presents a method for visible-thermal person re-identification.
Recommended citation: Jambigi, Chaitra et al. “MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID.” British Machine Vision Conference (2021)..
Download Paper
DAD: Data-free Adversarial Defense at Test Time
Published in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
A novel test-time adversarial defense method that detects and corrects adversarial samples without requiring training data, significantly improving robustness.
Recommended citation: G.K. Nayak, R. Rawal, A. Chakraborty. (2022). "DAD: Data-free Adversarial Defense at Test Time." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.
Download Paper
DE-CROP: Data-efficient certified robustness for pretrained classifiers
Published in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
DE-CROP enhances certified robustness of pretrained models with limited data by generating diverse samples and optimizing denoiser training in logit space.
Recommended citation: Nayak, Gaurav Kumar, Ruchit Rawal, and Anirban Chakraborty. "DE-CROP: Data-efficient certified robustness for pretrained classifiers." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023.
Download Paper
What happens during finetuning of vision transformers: An invariance based investigation
Published in Conference on Lifelong Learning Agents (CoLLAs), 2023
Pretraining induces transferable invariances, which are retained in shallow layers and compressed during finetuning, shedding light on why pretrained models excel.
Recommended citation: Merlin, Gabriele, et al. "What happens during finetuning of vision transformers: An invariance based investigation." Conference on Lifelong Learning Agents. PMLR, 2023.
Download Paper
Cinepile: A long video question answering dataset and benchmark
Published in Preprint, 2024
This paper introduces a dataset and benchmark for long video question answering.
Recommended citation: R. Rawal, K. Saifullah, M. Farré, R. Basri, D. Jacobs, G. Somepalli, et al. (2024). "Cinepile: A long video question answering dataset and benchmark." arXiv preprint arXiv:2405.08813.
Download Paper
Perturbed examples reveal invariances shared by language models
Published in Findings of the Association for Computational Linguistics (ACL), 2024
A framework to compare NLP models by analyzing their shared invariances to linguistic perturbations, offering insights into model evolution and performance.
Recommended citation: Rawal, Ruchit, and Mariya Toneva. "Perturbed examples reveal invariances shared by language models." Findings of the Association for Computational Linguistics: ACL 2024
Download Paper
Robust Few-Shot Learning Without Using Any Adversarial Samples
Published in IEEE Transactions on Neural Networks and Learning Systems (IEEE-TNNLS), 2024
A simple yet effective self-distillation approach enhances adversarial robustness in few-shot learning without requiring adversarial samples, achieving significant improvements with minimal computational overhead.
Recommended citation: Nayak, Gaurav Kumar, et al. "Robust Few-Shot Learning Without Using Any Adversarial Samples." IEEE Transactions on Neural Networks and Learning Systems (2024).
Download Paper
Hints Help Finding and Fixing Bugs Differently in Python and Text-based Program Representations
Published in International Conference on Software Engineering (ICSE), 2025
This paper explores how natural language representations and different types of hints influence end-user debugging accuracy in AI-assisted programming.
Recommended citation: Rawal, Ruchit, et al. "Hints Help Finding and Fixing Bugs Differently in Python and Text-based Program Representations." arXiv preprint arXiv:2412.12471 (2024).
Download Paper
talks
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.