Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection

TL;DR

This paper introduces a dual pseudo-label polishing framework for semi-supervised object detection, significantly improving label accuracy and model performance by refining pseudo labels through specialized networks and disentangling categories from bounding boxes.

Contribution

The paper proposes a novel dual polishing learning scheme and label disentanglement method to enhance pseudo label quality in semi-supervised object detection.

Findings

Outperforms existing state-of-the-art methods on PASCAL VOC and MS COCO.

Improves pseudo label accuracy through dual polishing networks.

Enables more effective use of unannotated objects in training.

Abstract

Exploiting pseudo labels (e.g., categories and bounding boxes) of unannotated objects produced by a teacher detector have underpinned much of recent progress in semi-supervised object detection (SSOD). However, due to the limited generalization capacity of the teacher detector caused by the scarce annotations, the produced pseudo labels often deviate from ground truth, especially those with relatively low classification confidences, thus limiting the generalization performance of SSOD. To mitigate this problem, we propose a dual pseudo-label polishing framework for SSOD. Instead of directly exploiting the pseudo labels produced by the teacher detector, we take the first attempt at reducing their deviation from ground truth using dual polishing learning, where two differently structured polishing networks are elaborately developed and trained using synthesized paired pseudo labels and the corresponding ground truth for categories and bounding boxes on the given annotated objects, respectively. By doing this, both polishing networks can infer more accurate pseudo labels for unannotated objects through sufficiently exploiting their context knowledge based on the initially produced pseudo labels, and thus improve the generalization performance of SSOD. Moreover, such a scheme can be seamlessly plugged into the existing SSOD framework for joint end-to-end learning. In addition, we propose to disentangle the polished pseudo categories and bounding boxes of unannotated objects for separate category classification and bounding box regression in SSOD, which enables introducing more unannotated objects during model training and thus further improve the performance. Experiments on both PASCAL VOC and MS COCO benchmarks demonstrate the superiority of the proposed method over existing state-of-the-art baselines.