SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction

2026-09-16

AI Summary

本文提出SPARC，一种基于超像素的区域对比学习框架，用于自监督密集预测任务，通过引入区域对比分支优化区域级和全局目标。

Abstract

Self-supervised learning (SSL) has become an effective approach for learning visual representations without manual annotations. Among SSL approaches, contrastive learning has been widely used for visual representation learning. However, existing contrastive SSL methods have focused primarily on image-level or pixel-level representation learning, while region-level representation learning remains less explored. We propose SPARC, a region-level contrastive learning framework that leverages superpixels to establish explicit correspondence between augmented image views. SPARC introduces a region contrastive branch that performs superpixel-based feature pooling and optimizes a region-level contrastive objective jointly with a global image-level objective. Under identical settings, SPARC consistently outperforms previous methods such as MoCo-v2 and DenseCL, achieving improvements of up to +9.79 mIoU for semantic segmentation and +4.88 AP for object detection. Ablation studies further demonstrate that region-level objectives produce the strongest performance. Thus, region-level contrastive learning is an effective approach for improving self-supervised visual pretraining for dense prediction tasks. Code repository can be accessed at https://github.com/xRIPEIx/SPARC.

Problem

• contrastive learning
• region-level representation
• self-supervised learning
• dense prediction

Innovation

• superpixel-based feature pooling
• region-level contrastive learning
• self-supervised dense prediction