paper-with-me

홈 › Papers

Knowledge Distillation with Deep Supervision

2022-02-16 · Shiya Luo, Defang Chen, Can Wang

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only used to provide the supervisory signal for the last layer of the student model, which may result in those shallow student layers lacking accurate training guidance in the layer-by-layer back propagation and thus hinders effective knowledge transfer. To address this issue, we propose Deeply-Supervised Knowledge Distillation (DSKD), which fully utilizes class predictions and feature maps of the teacher model to supervise the training of shallow student layers. A loss-based weight allocation strategy is developed in DSKD to adaptively balance the learning process of each shallow layer, so as to further improve the student performance. Extensive experiments on CIFAR-100 and TinyImageNet with various teacher-student models show significantly performance, confirming the effectiveness of our proposed method. Code is available at: $\href{https://github.com/luoshiya/DSKD}{https://github.com/luoshiya/DSKD}$

📄 PDF Abstract BibTeX arXiv:2202.07846

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Knowledge Distillation Meets Self-Supervision

2020-06-12 · ECCV 2020 8 · Guodong Xu, Ziwei Liu, Xiaoxiao Li, Chen Change Loy

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning.…

Contrastive LearningKnowledge DistillationModel CompressionTransfer Learning

Preparing Lessons: Improve Knowledge Distillation with Better Supervision

2019-11-18 · Tiancheng Wen, Shenqi Lai, Xueming Qian

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) train…

Knowledge Distillation

Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models

2026-03-22 · Jingchen Sun, Shaobo Han, Deep Patel, Wataru Kohno 외 arxiv

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is chall…

Knowledge Distillation

VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition

2024-08-29 · Zaiwei Zhang, Gregory P. Meyer, Zhichao Lu, Ashish Shrivastava 외

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill kno…

Knowledge DistillationLanguage ModelingLanguage Modelling

Supervision Complexity and its Role in Knowledge Distillation

2023-01-28 · Hrayr Harutyunyan, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim 외

Despite the popularity and efficacy of knowledge distillation, there is limited understanding of why it helps. In order to study the generalization behavior of a distilled student, we propose a new theoretical framework …

image-classificationImage ClassificationKnowledge Distillation