paper-with-me

Papers

CORSD: Class-Oriented Relational Self Distillation

2023-04-28 · Muzhou Yu, Sia Huat Tan, Kailu Wu, Runpei Dong, Linfeng Zhang, Kaisheng Ma

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data examples; (2) the relational distillation methods are either limited to the handcrafted functions for relation extraction, such as L2 norm, or weak in inter- and intra- class relation modeling. Besides, the feature divergence of heterogeneous teacher-student architectures may lead to inaccurate relational knowledge transferring. In this work, we propose a novel training framework named Class-Oriented Relational Self Distillation (CORSD) to address the limitations. The trainable relation networks are designed to extract relation of structured data input, and they enable the whole model to better classify samples by transferring the relational knowledge from the deepest layer of the model to shallow layers. Besides, auxiliary classifiers are proposed to make relation networks capture class-oriented relation that benefits classification task. Experiments demonstrate that CORSD achieves remarkable improvements. Compared to baseline, 3.8%, 1.5% and 4.5% averaged accuracy boost can be observed on CIFAR100, ImageNet and CUB-200-2011, respectively.

📄 PDF Abstract BibTeX arXiv:2305.00918

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationModel CompressionRelationRelation Extraction

Similar Papers 제목 키워드 기반

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

2026-07-28 · Yuqi Li, Yi-Cheng Lin, Xianglong Wang, Kuo Yang 외 arxiv

On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models that excel at SER are too costly for edge devices. Multi-teacher knowledge distillation can compress the…

Speech Emotion RecognitionKnowledge Distillation

STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation

2026-05-12 · Shuhan Ye, Yi Yu, Qixin Zhang, Hui Lu 외 arxiv

SNNs promise energy-efficient and low-latency inference, but their performance still trails that of ANNs. ANN-to-SNN knowledge distillation helps narrow this gap, yet the original training data are often unavailable in p…

Data-free Knowledge Distillation

Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection

2024-05-28 · Juntae Kim, Sungwon Woo, Jongho Nang

Image copy detection is the task of detecting edited copies of any image within a reference database. While previous approaches have shown remarkable progress, the large size of their networks and descriptors remains a d…

Contrastive LearningCopy Detection

SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images

2022-03-22 · Yongwei Wang, Yuheng Wang, Tim K. Lee, Chunyan Miao 외

Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Over the last few years, computer-aided diagnosis has been rapidly developed and make…

Knowledge DistillationLesion ClassificationSkin Lesion Classification

Image-to-Lidar Relational Distillation for Autonomous Driving Data

2024-09-01 · Anas Mahmoud, Ali Harakeh, Steven Waslander

Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust representations. The emergence of 2D-to-3D dist…

3D Semantic SegmentationAutonomous DrivingFew-shot 3D semantic segmentationSemantic Segmentation+2