Cascade R-CNN: Delving into High Quality Object Detection

12/03/2017
by   Zhaowei Cai, et al.
0

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 will be made available at https://github.com/zhaoweicai/cascade-rcnn.

READ FULL TEXT

page 1

page 4

research
06/24/2019

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

In object detection, the intersection over union (IoU) threshold is freq...
research
11/15/2022

3D Cascade RCNN: High Quality Object Detection in Point Clouds

Recent progress on 2D object detection has featured Cascade RCNN, which ...
research
12/27/2019

Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization

The majority of current object detectors lack context: class predictions...
research
03/22/2018

Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection

Recent years have witnessed many exciting achievements for object detect...
research
12/11/2019

IoU-uniform R-CNN: Breaking Through the Limitations of RPN

Region Proposal Network (RPN) is the cornerstone of two-stage object det...
research
04/03/2021

Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing

Within the field of instance segmentation, most of the state-of-the-art ...
research
07/16/2019

Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection

Recent researches attempt to improve the detection performance by adopti...

Please sign up or login with your details

Forgot password? Click here to reset