IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation
This addresses the annotation cost bottleneck in semantic segmentation for computer vision applications, though it appears incremental as an extension of existing teacher-student frameworks.
The paper tackles the problem of limited labeled data in semantic segmentation by proposing IPixMatch, a semi-supervised method that incorporates inter-pixel relations into teacher-student networks, achieving consistent performance improvements across multiple benchmark datasets.
The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to mine the neglected but valuable Inter-Pixel information for semi-supervised learning. Specifically, IPixMatch is constructed as an extension of the standard teacher-student network, incorporating additional loss terms to capture inter-pixel relations. It shines in low-data regimes by efficiently leveraging the limited labeled data and extracting maximum utility from the available unlabeled data. Furthermore, IPixMatch can be integrated seamlessly into most teacher-student frameworks without the need of model modification or adding additional components. Our straightforward IPixMatch method demonstrates consistent performance improvements across various benchmark datasets under different partitioning protocols.