Self-Supervised Learning of Pretext-Invariant Representations
This addresses the challenge of reducing reliance on labeled data for computer vision tasks, representing a significant advance in self-supervised learning.
The paper tackled the problem of learning semantically meaningful image representations without semantic annotations by proposing Pretext-Invariant Representation Learning (PIRL), which learns invariant rather than covariant representations under image transformations. It achieved state-of-the-art results on self-supervised learning benchmarks and outperformed supervised pre-training for object detection.
The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many pretext tasks lead to representations that are covariant with image transformations. We argue that, instead, semantic representations ought to be invariant under such transformations. Specifically, we develop Pretext-Invariant Representation Learning (PIRL, pronounced as "pearl") that learns invariant representations based on pretext tasks. We use PIRL with a commonly used pretext task that involves solving jigsaw puzzles. We find that PIRL substantially improves the semantic quality of the learned image representations. Our approach sets a new state-of-the-art in self-supervised learning from images on several popular benchmarks for self-supervised learning. Despite being unsupervised, PIRL outperforms supervised pre-training in learning image representations for object detection. Altogether, our results demonstrate the potential of self-supervised learning of image representations with good invariance properties.