paper-with-me

Papers

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

2024-03-10 · Liyang He, Zhenya Huang, Jiayu Liu, Enhong Chen, Fei Wang, Jing Sha, Shijin Wang

Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://github.com/hly1998/BRCD.

📄 PDF Abstract BibTeX arXiv:2403.06071

Code (1)

hly1998/brcd 공식 구현 pytorch

Tasks

Image RetrievalKnowledge DistillationModel Compression

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

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

2022-08-25 · CVPR 2023 1 · Xiaoyi Dong, Jianmin Bao, Yinglin Zheng, Ting Zhang 외

This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to dis…

Representation Learning

Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion

2026-05-08 · Yijing Wang, Ruonan Li, Qilin Wang, Rongqiang Zhao 외 arxiv

LiDAR-based semantic segmentation is essential for autonomous-driving perception, yet dense point-wise annotations are costly, and long-tailed outdoor scenes make small safety-critical objects difficult to discover witho…

Scene UnderstandingAutonomous DrivingPoint Clouds

RankCSE: Unsupervised Representation Learning via Learning to Rank

2022-11-14 · Anonymous

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives h…

Contrastive LearningLearning-To-RankRepresentation LearningSemantic Textual Similarity+2

RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank

2023-05-26 · Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang 외

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives h…

Contrastive LearningLearning-To-RankRepresentation LearningSemantic Textual Similarity+2

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation

2023-12-07 · Jiawei Fan, Chao Li, Xiaolong Liu, Meina Song 외

In recent years, knowledge distillation methods based on contrastive learning have achieved promising results on image classification and object detection tasks. However, in this line of research, we note that less atten…

Contrastive LearningData Augmentationimage-classificationImage Classification+5