Weakly Supervised Object Localization and Detection: A Survey

By Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

321 citations recorded by the source corpus.

As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9f1964b0e0c486e972a95f213bc5eda8c2fb7a65

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Gong Cheng
2. Junwei Han
3. Xiwen Yao
4. Ke Yan
5. Xiang Yuan
6. Qinghua Zeng
7. Peicheng Zhou
8. Lei Guo

Citations in the corpus

• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “Quite a number of surveys about object detection have been published in recent years [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], and our review differs from the existing ones mainly in two aspects.”
• Object Detection in 20 Years: A Survey (2019, unknown): “Weakly supervised object detection (WSOD) aims at easing the reliance on data annotation by training a detector with only image-level annotations instead of bounding boxes [201].”
• Residual Tuning: Toward Novel Category Discovery Without Labels (2022, unknown): “In particular, an increasing number of weakly supervised object detection (WSOD) approaches [67], [68] have been proposed since many of the images are simply annotated with image-level labels without bounding box annotations.”