paper-with-me

홈 › Papers

Dynamic Temperature Knowledge Distillation

2024-04-19 · Yukang Wei, Yu Bai

Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD). Traditional approaches often employ a static temperature throughout the KD process, which fails to address the nuanced complexities of samples with varying levels of difficulty and overlooks the distinct capabilities of different teacher-student pairings. This leads to a less-than-ideal transfer of knowledge. To improve the process of knowledge propagation, we proposed Dynamic Temperature Knowledge Distillation (DTKD) which introduces a dynamic, cooperative temperature control for both teacher and student models simultaneously within each training iterafion. In particular, we proposed "\textbf{sharpness}" as a metric to quantify the smoothness of a model's output distribution. By minimizing the sharpness difference between the teacher and the student, we can derive sample-specific temperatures for them respectively. Extensive experiments on CIFAR-100 and ImageNet-2012 demonstrate that DTKD performs comparably to leading KD techniques, with added robustness in Target Class KD and None-target Class KD scenarios.The code is available at https://github.com/JinYu1998/DTKD.

📄 PDF Abstract BibTeX arXiv:2404.12711

Code (1)

JinYu1998/DTKD 공식 구현 pytorch

Tasks

Knowledge 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

Curriculum Temperature for Knowledge Distillation

2022-11-29 · Zheng Li, Xiang Li, Lingfeng Yang, Borui Zhao 외

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls …

Image ClassificationKnowledge Distillation

LLM-Oriented Token-Adaptive Knowledge Distillation

2025-10-13 · Xurong Xie, Zhucun Xue, Jiafu Wu, Jian Li 외 arxiv

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning proce…

Knowledge Distillation

Dynamic Temperature Scheduler for Knowledge Distillation

2025-11-14 · Sibgat Ul Islam, Jawad Ibn Ahad, Fuad Rahman, Mohammad Ruhul Amin 외 arxiv

Knowledge Distillation (KD) trains a smaller student model using a large, pre-trained teacher model, with temperature as a key hyperparameter controlling the softness of output probabilities. Traditional methods use a fi…

Knowledge Distillation

Adaptive Temperature Based on Logits Correlation in Knowledge Distillation

2025-03-12 · Kazuhiro Matsuyama, Usman Anjum, Satoko Matsuyama, Tetsuo Shoda 외

Knowledge distillation is a technique to imitate a performance that a deep learning model has, but reduce the size on another model. It applies the outputs of a model to train another model having comparable accuracy. Th…

Knowledge Distillation

Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework

2022-12-16 · Junzhuo Li, Xinwei Wu, Weilong Dong, Shuangzhi Wu 외

Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a small student model. However, despite the …

Knowledge DistillationModel CompressionPrivacy PreservingTransfer Learning