CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection
This addresses a key bottleneck in semi-supervised object detection for computer vision applications, offering an incremental improvement over existing self-labeling methods.
The paper tackles the problem of self-errors in semi-supervised object detection, where incorrect pseudo labels from the detector itself limit performance, and proposes CrossRectify, which uses two detectors to identify and rectify these errors, achieving outperforming results on 2D and 3D benchmarks.
Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and unlabeled data with pseudo labels predicted by the detector itself, but their performances are always limited. Through experimental analysis, we reveal the underlying reason is that the detector is misguided by the incorrect pseudo labels predicted by itself (dubbed self-errors). These self-errors can hurt performance even worse than random-errors, and can be neither discerned nor rectified during the self-labeling process. In this paper, we propose an effective detection framework named CrossRectify, to obtain accurate pseudo labels by simultaneously training two detectors with different initial parameters. Specifically, the proposed approach leverages the disagreements between detectors to discern the self-errors and refines the pseudo label quality by the proposed cross-rectifying mechanism. Extensive experiments show that CrossRectify achieves outperforming performances over various detector structures on 2D and 3D detection benchmarks.