Cascade R-CNN: Delving into High Quality Object Detection

TL;DR

Cascade R-CNN introduces a multi-stage detection architecture that trains detectors with increasing IoU thresholds, improving high-quality object detection performance by reducing overfitting and inference mismatch.

Contribution

It proposes a novel cascade architecture that sequentially trains detectors at higher IoU thresholds, enhancing detection accuracy and robustness across various architectures.

Findings

Outperforms all single-model detectors on COCO dataset

Achieves consistent improvements across different detector architectures

Reduces overfitting by resampling progressively improved hypotheses

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