Self-Supervised Visual Representation Learning with Semantic Grouping

TL;DR

This paper introduces SlotCon, a contrastive learning method that uses data-driven semantic slots to improve visual representation learning from unlabeled scene-centric data, enhancing scene decomposition and downstream task performance.

Contribution

The paper proposes a novel contrastive learning framework with learnable semantic prototypes for joint scene grouping and representation learning, avoiding hand-crafted priors.

Findings

Effective scene decomposition into semantic groups.

Improved performance on object detection, segmentation tasks.

Learned representations enhance discriminability and generalization.

Abstract

In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they commonly rely on hand-crafted objectness priors or specialized pretext tasks to build a learning framework, which may harm generalizability. Instead, we propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning. The semantic grouping is performed by assigning pixels to a set of learnable prototypes, which can adapt to each sample by attentive pooling over the feature and form new slots. Based on the learned data-dependent slots, a contrastive objective is employed for representation learning, which enhances the discriminability of features, and conversely facilitates grouping semantically coherent pixels together. Compared with previous efforts, by simultaneously optimizing the two coupled objectives of semantic grouping and contrastive learning, our approach bypasses the disadvantages of hand-crafted priors and is able to learn object/group-level representations from scene-centric images. Experiments show our approach effectively decomposes complex scenes into semantic groups for feature learning and significantly benefits downstream tasks, including object detection, instance segmentation, and semantic segmentation. Code is available at: https://github.com/CVMI-Lab/SlotCon.