Cascade R-CNN: Delving Into High Quality Object Detection
Top Cited Papers
- 1 June 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6154-6162
- https://doi.org/10.1109/cvpr.2018.00644
Abstract
In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code is available at https://github.com/zhaoweicai/cascade-rcnn.Keywords
This publication has 24 references indexed in Scilit:
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- AttentionNet: Aggregating Weak Directions for Accurate Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Object Detection via a Multi-region and Semantic Segmentation-Aware CNN ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A convolutional neural network cascade for face detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Learn to Combine Multiple Hypotheses for Accurate Face AlignmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004