Co-occurrence matrix analysis-based semi-supervised training for object detection

TL;DR

This paper introduces a semi-supervised training approach for object detection that leverages co-occurrence matrix analysis to improve label quality of unannotated data, enhancing detector performance without extra parameters.

Contribution

It proposes a novel re-alignment method based on co-occurrence matrices to refine pseudo-labels in semi-supervised learning for object detection.

Findings

Improved detection accuracy on MS-COCO dataset

Enhancement of state-of-the-art detectors without additional parameters

Effective use of co-occurrence analysis for label re-alignment

Abstract

One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset. Because an inferred label by the trained network is dependent on the learned parameters, it is often meaningless for re-training the network. To transfer a valuable inferred label to the unlabeled data, we propose a re-alignment method based on co-occurrence matrix analysis that takes into account one-hot-vector encoding of the estimated label and the correlation between the objects in the image. We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) as an object detector for basic training. The performance of the existing state-of-the-art detectors (DConvNets, YOLO v2, and single shot multi-box detector (SSD)) can be improved by the proposed SSL method without using the additional model parameter or modifying the network architecture.