Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects

By Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki. 2018

46 citations recorded by the source corpus.

Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large datasets like Open Images Dataset v4 (OID) are sparsely annotated, and some measure must be taken in order to ensure the training of a reliable detector. In order to take the incompleteness of these datasets into account, one possibility is to use pretrained models to detect the presence of the unverified objects. However, the performance of such a strategy depends largely on the power of the pretrained model. In this study, we propose part-aware sampling, a method that uses human intuition for the hierarchical relation between objects. In terse terms, our method works by making assumptions like “a bounding box for a car should contain a bounding box for a tire”. We demonstrate the power of our method on OID and compare the performance against a method based on a pretrained model. Our method also won the first and second place on the public and private test sets of the Google AI Open Images Competition 2018.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

1. Zhiqiang Shen
2. Marios Savvides
3. Fangyi Chen
4. Chenchen Zhu
5. Tianfang Zhao
6. Han Zhang
7. Yuan Shen
8. Qiqi Hao

In Computer Vision and Pattern Recognition

1. Zhiqiang Shen
2. Marios Savvides
3. Fangyi Chen
4. Chenchen Zhu
5. Tianfang Zhao
6. Han Zhang
7. Yuan Shen
8. Qiqi Hao

Citations in the corpus

• EPicker is an exemplar-based continual learning approach for knowledge accumulation in cryoEM particle picking (2022, methodology): “Some previous works dealing with sparse annotation in natural images solved this problem by reweighting the importance of region proposals generated by the two-stage object detector Faster RCNN 38,39 or recalibrating the loss of the anchors used by the one-stage object detector YOLO 40 .”
• Solving Missing-Annotation Object Detection with Background Recalibration Loss (2020, methodology): “In the recent years, a variety of two-stage detector based methods have been proposed, such as part-aware sampling [6] and soft sampling [1].”