Can I read Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning on EtoBox?

Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning by Zhang, Shaofeng; Zhu, Feng; Zhao, Rui; Yan, Junchi is a scholarly article available to read on EtoBox.

What is Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning about?

We propose ADCLR: A ccurate and D ense Contrastive Representation Learning, a novel self-supervised learning framework for learning accurate and dense vision representation. To extract spatial-sensitive information, ADCLR introduces query patches for contrasting in addition with global contrasting. Compared with previous dense contrasting methods, ADCLR mainly enjoys three merits: i) achieving both global-discriminative and spatial-sensitive representation, ii) model-efficient (no extra parameters in addition to the global contrasting baseline), and iii) correspondence-free and thus simpler to implement. Our approach achieves new state-of-the-art performance for contrastive methods. On classification tasks, for ViT-S, ADCLR achieves 77.5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0.5%. For ViT-B, ADCLR achieves 79.8%, 84.0% accuracy on ImageNet by linear probing and finetune, outperforming iBOT by 0.3%, 0.2% accuracy. For dense tasks, on MS-COCO, ADCLR achieves significant improvements of 44.3% AP on object detection, 39.7% AP on instance segmentation, outperforming previous SOTA method SelfPatch

Author

Zhang, Shaofeng; Zhu, Feng; Zhao, Rui; Yan, Junchi

Published

2023

Language

EN