paper-with-me

홈 › Papers

MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face Recognition

2024-08-29 · Eduarda Caldeira, Jaime S. Cardoso, Ana F. Sequeira, Pedro C. Neto

As in school, one teacher to cover all subjects is insufficient to distill equally robust information to a student. Hence, each subject is taught by a highly specialised teacher. Following a similar philosophy, we propose a multiple specialized teacher framework to distill knowledge to a student network. In our approach, directed at face recognition use cases, we train four teachers on one specific ethnicity, leading to four highly specialized and biased teachers. Our strategy learns a project of these four teachers into a common space and distill that information to a student network. Our results highlighted increased performance and reduced bias for all our experiments. In addition, we further show that having biased/specialized teachers is crucial by showing that our approach achieves better results than when knowledge is distilled from four teachers trained on balanced datasets. Our approach represents a step forward to the understanding of the importance of ethnicity-specific features.

📄 PDF Abstract BibTeX arXiv:2408.16563

Code (1)

eduardacaldeira/mst-kd 공식 구현 pytorch

Tasks

Face RecognitionKnowledge DistillationPhilosophy

Similar Papers 제목 키워드 기반

Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model

2024-02-21 · Zichang Liu, Qingyun Liu, Yuening Li, Liang Liu 외

Recent advancements in foundation models have yielded impressive performance across a wide range of tasks. Meanwhile, for specific applications, practitioners have been developing specialized application models. To enjoy…

Knowledge DistillationmodelTransfer Learning

Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning

2023-06-11 · Hailin Zhang, Defang Chen, Can Wang

Multi-Teacher knowledge distillation provides students with additional supervision from multiple pre-trained teachers with diverse information sources. Most existing methods explore different weighting strategies to obta…

Knowledge DistillationMeta-Learning

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

2026-08-04 · Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei 외 arxiv

Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multili…

Reinforcement Learning

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation

2025-07-09 · Hui Li, Pengfei Yang, Juanyang Chen, Le Dong 외 arxiv

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challe…

Knowledge Distillation

Building a Multi-domain Neural Machine Translation Model using Knowledge Distillation

2020-04-15 · Idriss Mghabbar, Pirashanth Ratnamogan

Lack of specialized data makes building a multi-domain neural machine translation tool challenging. Although emerging literature dealing with low resource languages starts to show promising results, most state-of-the-art…

Domain AdaptationKnowledge DistillationMachine TranslationTranslation