Title | ||
---|---|---|
A progressive learning framework based on single-instance annotation for weakly supervised object detection |
Abstract | ||
---|---|---|
Fully-supervised object detection (FSOD) and weakly-supervised object detection (WSOD) are two extremes in the field of object detection. The former relies entirely on detailed bounding-box annotations while the later discards them completely. To balance these two extremes, we propose to make use of the so-called single-instance annotations, i.e., all images that contain only a single object are labeled with the corresponding bounding-boxes. By using such instance annotations of the simplest images, we propose a progressive learning framework that integrates image-level learning, single-instance learning, and multi-instance learning into an end-to-end network. Specifically, our framework is composed of three parallel streams that share a proposal feature extractor. The first stream is supervised by image-level annotations, which provides global information of all training data for the shared feature extractor. The second stream is supervised by single-instance annotations to bridge the features learning gap between the image level and instance level. To further learn from complex images, we propose an overlap-based instance mining algorithm to mine pseudo multi-instance annotations from the detection results of the second stream, and use them to supervise the third stream. Our method achieves a trade-off between the detection accuracy and annotation cost. Extensive experiments demonstrate the effectiveness of our proposed method on the PASCAL VOC and MS-COCO dataset, implying that a few single-instance annotations can improve the detection performance of WSOD significantly (more than 10%) and reduce the average annotation cost of FSOD greatly (more than 5 times). |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.cviu.2020.102903 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
Single-instance annotation,Progressive learning framework,Weakly supervised object detection,Instance mining | Training set,Object detection,Annotation,Global information,Extractor,Artificial intelligence,Data mining algorithm,Machine learning,Mathematics | Journal |
Volume | Issue | ISSN |
193 | 1 | 1077-3142 |
Citations | PageRank | References |
2 | 0.36 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ming Zhang | 1 | 89 | 18.62 |
B Zeng | 2 | 1374 | 159.35 |