paper-with-me

Papers

Towards a Unified View of Affinity-Based Knowledge Distillation

2022-09-30 · Vladimir Li, Atsuto Maki

Knowledge transfer between artificial neural networks has become an important topic in deep learning. Among the open questions are what kind of knowledge needs to be preserved for the transfer, and how it can be effectively achieved. Several recent work have shown good performance of distillation methods using relation-based knowledge. These algorithms are extremely attractive in that they are based on simple inter-sample similarities. Nevertheless, a proper metric of affinity and use of it in this context is far from well understood. In this paper, by explicitly modularising knowledge distillation into a framework of three components, i.e. affinity, normalisation, and loss, we give a unified treatment of these algorithms as well as study a number of unexplored combinations of the modules. With this framework we perform extensive evaluations of numerous distillation objectives for image classification, and obtain a few useful insights for effective design choices while demonstrating how relation-based knowledge distillation could achieve comparable performance to the state of the art in spite of the simplicity.

📄 PDF Abstract BibTeX arXiv:2209.15555

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationKnowledge DistillationRelationTransfer 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

VRM: Knowledge Distillation via Virtual Relation Matching

2025-02-28 · Weijia Zhang, Fei Xie, Weidong Cai, Chao Ma

Knowledge distillation (KD) aims to transfer the knowledge of a more capable yet cumbersome teacher model to a lightweight student model. In recent years, relation-based KD methods have fallen behind, as their instance-m…

Knowledge DistillationRelation

Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction

2026-01-07 · Wajid Arshad Abbasi, Syed Ali Abbas, Maryum Bibi, Saiqa Andleeb 외 arxiv

The trade-off between predictive accuracy and data availability makes it difficult to predict protein--protein binding affinity accurately. The lack of experimentally resolved protein structures limits the performance of…

Knowledge Distillation

Graph Relation Distillation for Efficient Biomedical Instance Segmentation

2024-01-12 · Xiaoyu Liu, Yueyi Zhang, Zhiwei Xiong, Wei Huang 외

Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring di…

Instance SegmentationKnowledge DistillationRelationSemantic Segmentation

High-order Correlation Preserved Incomplete Multi-view Subspace Clustering

2022-02-21 · IEEE Transactions on Image Processing 2022 2 · Zhenglai Li, Chang Tang, Xiao Zheng, Xinwang Liu 외

Incomplete multi-view clustering aims to exploit theinformation of multiple incomplete views to partition data into their clusters. Existing methods only utilize the pair-wise sample correlation and pair-wise view correl…

ClusteringIncomplete multi-view clusteringMulti-view Subspace ClusteringVocal Bursts Intensity Prediction

Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation

2023-04-28 · Shoumeng Qiu, Feng Jiang, Haiqiang Zhang, xiangyang xue 외

3D point cloud semantic segmentation is one of the fundamental tasks for environmental understanding. Although significant progress has been made in recent years, the performance of classes with few examples or few point…

Knowledge DistillationSemantic Segmentation