Good Teachers Explain: Explanation-Enhanced Knowledge Distillation

1 code implementation • 5 Feb 2024 • Amin Parchami-Araghi, Moritz Böhle, Sukrut Rao, Bernt Schiele

Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models.

Knowledge Distillation

Using Explanations to Guide Models

1 code implementation • 21 Mar 2023 • Sukrut Rao, Moritz Böhle, Amin Parchami-Araghi, Bernt Schiele

To gain a better understanding of which model-guiding approaches actually transfer to more challenging real-world datasets, in this work we conduct an in-depth evaluation across various loss functions, attribution methods, models, and 'guidance depths' on the PASCAL VOC 2007 and MS COCO 2014 datasets, and show that model guidance can sometimes even improve model performance.

Better Understanding Differences in Attribution Methods via Systematic Evaluations

1 code implementation • 21 Mar 2023 • Sukrut Rao, Moritz Böhle, Bernt Schiele

Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.

Fairness

Studying How to Efficiently and Effectively Guide Models with Explanations

1 code implementation • ICCV 2023 • Sukrut Rao, Moritz Böhle, Amin Parchami-Araghi, Bernt Schiele

To better understand the effectiveness of the various design choices that have been explored in the context of model guidance, in this work we conduct an in-depth evaluation across various loss functions, attribution methods, models, and 'guidance depths' on the PASCAL VOC 2007 and MS COCO 2014 datasets.

Towards Better Understanding Attribution Methods

1 code implementation • CVPR 2022 • Sukrut Rao, Moritz Böhle, Bernt Schiele

Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.

Explanation Fidelity Evaluation Image Classification +1

Adversarial Training against Location-Optimized Adversarial Patches

1 code implementation • 5 May 2020 • Sukrut Rao, David Stutz, Bernt Schiele

Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB.

Approximation Strategies for Incomplete MaxSAT

1 code implementation • 19 Jun 2018 • Saurabh Joshi, Prateek Kumar, Ruben Martins, Sukrut Rao

Incomplete MaxSAT solving aims to quickly find a solution that attempts to minimize the sum of the weights of the unsatisfied soft clauses without providing any optimality guarantees.

Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification

3 code implementations • 7 Mar 2018 • Vaibhav B Sinha, Sukrut Rao, Vineeth N. Balasubramanian

A well-known approach for aggregation is the Dawid-Skene (DS) algorithm, which is based on the principle of Expectation-Maximization (EM).

General Classification Sentiment Analysis +1