C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks
This addresses the challenge of real-world object detection for computer vision applications, though it appears incremental as it builds on existing two-stage detectors like Faster R-CNN.
The paper tackles the problem of object detection in real-world scenarios where data imbalance between easy and hard samples limits existing methods, proposing C-RPNs which achieves competitive results on benchmarks like Pascal VOC and BSBDV 2017 with all-sided improvements in error analysis.
Recently, significant progresses have been made in object detection on common benchmarks (i.e., Pascal VOC). However, object detection in real world is still challenging due to the serious data imbalance. Images in real world are dominated by easy samples like the wide range of background and some easily recognizable objects, for example. Although two-stage detectors like Faster R-CNN achieved big successes in object detection due to the strategy of extracting region proposals by region proposal network, they show their poor adaption in real-world object detection as a result of without considering mining hard samples during extracting region proposals. To address this issue, we propose a Cascade framework of Region Proposal Networks, referred to as C-RPNs. The essence of C-RPNs is adopting multiple stages to mine hard samples while extracting region proposals and learn stronger classifiers. Meanwhile, a feature chain and a score chain are proposed to help learning more discriminative representations for proposals. Moreover, a loss function of cascade stages is designed to train cascade classifiers through backpropagation. Our proposed method has been evaluated on Pascal VOC and several challenging datasets like BSBDV 2017, CityPersons, etc. Our method achieves competitive results compared with the current state-of-the-arts and all-sided improvements in error analysis, validating its efficacy for detection in real world.