Sukrut Rao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sukrut Rao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Bernt Schiele
Max Planck Institute for Informatics, Saarbrücken, Germany
6 shared publications - Moritz Böhle
Max Planck Institute for Informatics, Saarland Informatics Campus
3 shared publications - Amin Parchami-Araghi
Max Planck Institute for Informatics, Saarland Informatics Campus
2 shared publications - David Stutz
Google DeepMind, London, UK
2 shared publications - Prateek Kumar
Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Kandi, Sangareddy, Telangana - 502285, India. s
2 shared publications - Saurabh Joshi
Indian Institute of Technology Hyderabad
2 shared publications
Latest Publications
- 13 September 2026
- Published by Springer Nature
- p. 173-191
CFM: Language-Aligned Concept Foundation Model for Vision
- 13 September 2026
- Published by Springer Nature
- p. 173-191
CFM: Language-Aligned Concept Foundation Model for Vision
- 4 December 2024
- Published by Springer Nature
- p. 293-310
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
- 4 December 2024
- Published by Springer Nature
- p. 293-310
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
- 29 October 2024
- Published by Springer Nature
- p. 444-461
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
- 29 October 2024
- Published by Springer Nature
- p. 444-461
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
- 12 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (6) , 4090-4101
Better Understanding Differences in Attribution Methods via Systematic Evaluations
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models’ decisions. Evaluating such methods is challenging since no ground truth attributions exist. We thus propose three novel evaluation schemes to more reliably measure the faithfulness of those methods, to make comparisons between them more fair , and to make visual inspection more systematic . To address faithfulness, we propose a novel evaluation setting (DiFull) in which we carefully control which parts of the input can influence the output in order to distinguish possible from impossible attributions. To address fairness, we note that different methods are applied at different layers, which skews any comparison, and so evaluate all methods on the same layers (ML-Att) and discuss how this impacts their performance on quantitative metrics. For more systematic visualizations, we propose a scheme (AggAtt) to qualitatively evaluate the methods on complete datasets. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models. Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.
- 12 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (6) , 4090-4101
Better Understanding Differences in Attribution Methods via Systematic Evaluations
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models’ decisions. Evaluating such methods is challenging since no ground truth attributions exist. We thus propose three novel evaluation schemes to more reliably measure the faithfulness of those methods, to make comparisons between them more fair , and to make visual inspection more systematic . To address faithfulness, we propose a novel evaluation setting (DiFull) in which we carefully control which parts of the input can influence the output in order to distinguish possible from impossible attributions. To address fairness, we note that different methods are applied at different layers, which skews any comparison, and so evaluate all methods on the same layers (ML-Att) and discuss how this impacts their performance on quantitative metrics. For more systematic visualizations, we propose a scheme (AggAtt) to qualitatively evaluate the methods on complete datasets. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models. Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.
- Open Access
Adversarial Training against Location-Optimized Adversarial Patches
Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.
Open AccessAdversarial Training against Location-Optimized Adversarial Patches
Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.
- 1 January 2020
- Published by Springer Nature
- p. 429-448
Adversarial Training Against Location-Optimized Adversarial Patches
- 1 January 2020
- Published by Springer Nature
- p. 429-448
Adversarial Training Against Location-Optimized Adversarial Patches
- Open Access
- 1 September 2019
- Published by SAGE Publications in Journal on Satisfiability, Boolean Modeling and Computation
- Vol. 11 (1) , 73-97
Open-WBO-Inc: Approximation Strategies for Incomplete Weighted MaxSAT
Incomplete MaxSAT solving aims to quickly find a solution that attempts to minimize the sum of the weights of unsatisfied soft clauses without providing any optimality guarantees. In this paper, we propose two approximation strategies for improving i
- 1 September 2019
- Published by SAGE Publications in Journal on Satisfiability, Boolean Modeling and Computation
- Vol. 11 (1) , 73-97
Open AccessOpen-WBO-Inc: Approximation Strategies for Incomplete Weighted MaxSAT
Incomplete MaxSAT solving aims to quickly find a solution that attempts to minimize the sum of the weights of unsatisfied soft clauses without providing any optimality guarantees. In this paper, we propose two approximation strategies for improving i