paper-with-me

Papers

Group Distributionally Robust Knowledge Distillation

2023-11-01 · Konstantinos Vilouras, Xiao Liu, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris

Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-population shifts, a common scenario in medical imaging analysis which refers to groups/domains of data that are underrepresented in the training set. For instance, training models on health data acquired from multiple scanners or hospitals can yield subpar performance for minority groups. In this paper, inspired by distributionally robust optimization (DRO) techniques, we address this shortcoming by proposing a group-aware distillation loss. During optimization, a set of weights is updated based on the per-group losses at a given iteration. This way, our method can dynamically focus on groups that have low performance during training. We empirically validate our method, GroupDistil on two benchmark datasets (natural images and cardiac MRIs) and show consistent improvement in terms of worst-group accuracy.

📄 PDF Abstract BibTeX arXiv:2311.00476

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Group Distributionally Robust Dataset Distillation with Risk Minimization

2024-02-07 · Saeed Vahidian, Mingyu Wang, Jianyang Gu, Vyacheslav Kungurtsev 외

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its…

Dataset DistillationFederated LearningNeural Architecture SearchTransfer Learning

Grouped Knowledge Distillation for Deep Face Recognition

2023-04-10 · Weisong Zhao, Xiangyu Zhu, Kaiwen Guo, Xiao-Yu Zhang 외

Compared with the feature-based distillation methods, logits distillation can liberalize the requirements of consistent feature dimension between teacher and student networks, while the performance is deemed inferior in …

Face RecognitionKnowledge Distillation

Online Knowledge Distillation with Diverse Peers

2019-12-01 · Defang Chen, Jian-Ping Mei, Can Wang, Yan Feng 외

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, ho…

Knowledge DistillationTransfer Learning

ORC: Network Group-based Knowledge Distillation using Online Role Change

2022-06-01 · ICCV 2023 1 · Junyong Choi, Hyeon Cho, Seokhwa Cheung, Wonjun Hwang

In knowledge distillation, since a single, omnipotent teacher network cannot solve all problems, multiple teacher-based knowledge distillations have been studied recently. However, sometimes their improvements are not as…

Knowledge Distillation

Adaptive Group Robust Ensemble Knowledge Distillation

2024-11-22 · Patrik Kenfack, Ulrich Aïvodji, Samira Ebrahimi Kahou

Neural networks can learn spurious correlations in the data, often leading to performance disparity for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled fr…

Knowledge Distillation