Abstract
Contrastive image representation learning through instance discrimination has shown impressive transfer performance. Recent strategies have focused on pushing the limit of their transfer performance for dense prediction tasks, particularly when conducting pre-training on scene images with complex structures. Initial approaches employ pixel-level contrastive pre-training to optimize dense spatial features, while subsequent methods utilize region-mining algorithms to capture holistic regional semantics and address the issue of semantically inconsistent scene image crops. In this paper, we revisit pixel-level contrastive pre-training on scene images. Contrary to the assumption that pixel-level learning falls short in achieving these objectives, we demonstrate its under-explored potentials: (1) it can effectively learn holistic regional semantics more simply compared to region-level methods, and (2) it intrinsically provides tools to mitigate the impact of semantically inconsistent views involved with scene-level training images. We propose PixCon, a pixel-level contrastive learning framework, and explore two variants with different positive matching strategies to investigate the potential of pixel-level learning. Additionally, when PixCon incorporates a novel semantic reweighting approach tailored for scene image pre-training, it outperforms or matches the performance of previous region-level methods in object detection and semantic segmentation tasks across multiple benchmarks.
Zongshang Pang
PhD Student
Yuta Nakashima
Professor
Yuta Nakashima is a professor with Institute for Datability Science, Osaka University. His research interests include computer vision, pattern recognition, natural langauge processing, and their applications.
Hajime Nagahara
Professor
He is working on computer vision and pattern recognition. His main research interests lie in image/video recognition and understanding, as well as applications of natural language processing techniques.