paper-with-me

홈 › Papers

NormKD: Normalized Logits for Knowledge Distillation

2023-08-01 · Zhihao Chi, Tu Zheng, Hengjia Li, Zheng Yang, Boxi Wu, Binbin Lin, Deng Cai

Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potential when we re-investigate the temperature, which is a crucial hyper-parameter to soften the logit outputs. For most of the previous works, it was set as a fixed value for the entire distillation procedure. However, as the logits from different samples are distributed quite variously, it is not feasible to soften all of them to an equal degree by just a single temperature, which may make the previous work transfer the knowledge of each sample inadequately. In this paper, we restudy the hyper-parameter temperature and figure out its incapability to distill the knowledge from each sample sufficiently when it is a single value. To address this issue, we propose Normalized Knowledge Distillation (NormKD), with the purpose of customizing the temperature for each sample according to the characteristic of the sample's logit distribution. Compared to the vanilla KD, NormKD barely has extra computation or storage cost but performs significantly better on CIRAR-100 and ImageNet for image classification. Furthermore, NormKD can be easily applied to the other logit based methods and achieve better performance which can be closer to or even better than the feature based method.

📄 PDF Abstract BibTeX arXiv:2308.00520

Code (1)

gizi1/NormKD 공식 구현 pytorch

Tasks

image-classificationImage ClassificationKnowledge Distillation

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

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

2023-03-23 · ICCV 2023 1 · Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang 외

Knowledge Distillation (KD) uses the teacher's prediction logits as soft labels to guide the student, while self-KD does not need a real teacher to require the soft labels. This work unifies the formulations of the two t…

Knowledge DistillationSelf-Knowledge Distillation

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation

2024-06-19 · Minchong Li, Feng Zhou, Xiaohui Song

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increase…

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language Model

Peak-Controlled Logits Poisoning Attack in Federated Distillation

2024-07-25 · Yuhan Tang, Aoxu Zhang, Zhiyuan Wu, Bo Gao 외

Federated Distillation (FD) offers an innovative approach to distributed machine learning, leveraging knowledge distillation for efficient and flexible cross-device knowledge transfer without necessitating the upload of …

Knowledge DistillationTransfer 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

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation

2022-11-11 · Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan 외

Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient computations, knowledge distillation is widely…

Knowledge Distillation