paper-with-me

Papers

Semi-Online Knowledge Distillation

2021-11-23 · Zhiqiang Liu, Yanxia Liu, Chengkai Huang

Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student network, which is a one-way process. Recently, deep mutual learning (DML) has been proposed to help student networks learn collaboratively and simultaneously. However, to the best of our knowledge, KD and DML have never been jointly explored in a unified framework to solve the knowledge distillation problem. In this paper, we investigate that the teacher model supports more trustworthy supervision signals in KD, while the student captures more similar behaviors from the teacher in DML. Based on these observations, we first propose to combine KD with DML in a unified framework. Furthermore, we propose a Semi-Online Knowledge Distillation (SOKD) method that effectively improves the performance of the student and the teacher. In this method, we introduce the peer-teaching training fashion in DML in order to alleviate the student's imitation difficulty, and also leverage the supervision signals provided by the well-trained teacher in KD. Besides, we also show our framework can be easily extended to feature-based distillation methods. Extensive experiments on CIFAR-100 and ImageNet datasets demonstrate the proposed method achieves state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2111.11747

Code (1)

swlzq/Semi-Online-KD 공식 구현 pytorch

Tasks

Knowledge DistillationModel CompressionTransfer 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 for Road Detection based on cross-model Semi-Supervised Learning

2024-02-07 · Wanli Ma, Oktay Karakus, Paul L. Rosin

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online…

Knowledge DistillationRoad Segmentation

Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion Classification

2025-08-15 · Siyamalan Manivannan arxiv

Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain.…

Skin Lesion ClassificationKnowledge DistillationEnsemble Learning

Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

2026-03-07 · Kai Cheng, Hao Wang, Wei Guo, Weiwen Liu 외 arxiv

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deploymen…

Knowledge Distillation

Knowledge Distillation as Semiparametric Inference

2021-04-20 · ICLR 2021 1 · Tri Dao, Govinda M Kamath, Vasilis Syrgkanis, Lester Mackey

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation proc…

Knowledge DistillationModel Compression

Knowledge Distillation with BERT for Image Tag-Based Privacy Prediction

2021-09-01 · RANLP 2021 9 · Chenye Zhao, Cornelia Caragea

Text in the form of tags associated with online images is often informative for predicting private or sensitive content from images. When using privacy prediction systems running on social networking sites that decide wh…

Knowledge DistillationTAG