HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning

TL;DR

HoughCL introduces a Hough space-based approach to improve positive pair sampling in dense self-supervised learning, enhancing robustness and performance in dense prediction tasks without extra learnable parameters.

Contribution

The paper proposes HoughCL, a novel Hough space-based method for selecting positive pairs in dense self-supervised learning, addressing background clutter and outliers effectively.

Findings

HoughCL outperforms baseline methods in dense prediction tasks.

HoughCL is robust against background clutter and outliers.

The method requires no additional learnable parameters.

Abstract

Recently, self-supervised methods show remarkable achievements in image-level representation learning. Nevertheless, their image-level self-supervisions lead the learned representation to sub-optimal for dense prediction tasks, such as object detection, instance segmentation, etc. To tackle this issue, several recent self-supervised learning methods have extended image-level single embedding to pixel-level dense embeddings. Unlike image-level representation learning, due to the spatial deformation of augmentation, it is difficult to sample pixel-level positive pairs. Previous studies have sampled pixel-level positive pairs using the winner-takes-all among similarity or thresholding warped distance between dense embeddings. However, these naive methods can be struggled by background clutter and outliers problems. In this paper, we introduce Hough Contrastive Learning (HoughCL), a Hough space based method that enforces geometric consistency between two dense features. HoughCL achieves robustness against background clutter and outliers. Furthermore, compared to baseline, our dense positive pairing method has no additional learnable parameters and has a small extra computation cost. Compared to previous works, our method shows better or comparable performance on dense prediction fine-tuning tasks.