Guided Collaborative Training for Pixel-wise Semi-Supervised Learning
This addresses the problem of limited labeled data for pixel-wise tasks in computer vision, offering a generalizable solution that is not incremental but a novel framework.
The paper tackles the challenge of applying semi-supervised learning to pixel-wise tasks like segmentation and denoising, which suffer from dense outputs and task-specific dependencies, by proposing Guided Collaborative Training (GCT) with a flaw detector and collaborative constraints, resulting in outperforming state-of-the-art SSL methods across four vision tasks.
We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs. In addition, existing pixel-wise SSL approaches are only suitable for certain tasks as they usually require to use task-specific properties. In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. First, GCT addresses the issues caused by the dense outputs through a novel flaw detector. Second, the modules in GCT learn from unlabeled data collaboratively through two newly proposed constraints that are independent of task-specific properties. As a result, GCT can be applied to a wide range of pixel-wise tasks without structural adaptation. Our extensive experiments on four challenging vision tasks, including semantic segmentation, real image denoising, portrait image matting, and night image enhancement, show that GCT outperforms state-of-the-art SSL methods by a large margin. Our code available at: https://github.com/ZHKKKe/PixelSSL.