Multi-Label Self-Supervised Learning with Scene Images

TL;DR

This paper introduces MLS, a simple yet effective multi-label self-supervised learning method for scene images that avoids complex modules and achieves state-of-the-art results on multiple benchmarks.

Contribution

Proposes a novel multi-label classification approach for scene image SSL that simplifies the framework and improves performance without dense matching or object discovery modules.

Findings

Achieves state-of-the-art results on MS-COCO benchmarks.

Learns high-quality representations suitable for classification, detection, and segmentation.

Simplifies the SSL framework, making it easier to deploy and extend.

Abstract

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that instead of hinging on these strenuous operations, quality image representations can be learned by treating scene/multi-label image SSL simply as a multi-label classification problem, which greatly simplifies the learning framework. Specifically, multiple binary pseudo-labels are assigned for each input image by comparing its embeddings with those in two dictionaries, and the network is optimized using the binary cross entropy loss. The proposed method is named Multi-Label Self-supervised learning (MLS). Visualizations qualitatively show that clearly the pseudo-labels by MLS can automatically find semantically similar pseudo-positive pairs across different images to facilitate contrastive learning. MLS learns high quality representations on MS-COCO and achieves state-of-the-art results on classification, detection and segmentation benchmarks. At the same time, MLS is much simpler than existing methods, making it easier to deploy and for further exploration.