Revisiting RCNN: On Awakening the Classification Power of Faster RCNN

Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 453-468


Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks. In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization. We conjecture that: (1) Shared feature representation is not optimal due to the mismatched goals of feature learning for classification and localization; (2) multi-task learning helps, yet optimization of the multi-task loss may result in sub-optimal for individual tasks; (3) large receptive field for different scales leads to redundant context information for small objects. We demonstrate the potential of detector classification power by a simple, effective, and widely-applicable Decoupled Classification Refinement (DCR) network. DCR samples hard false positives from the base classifier in Faster RCNN and trains a RCNN-styled strong classifier. Experiments show new state-of-the-art results on PASCAL VOC and COCO without any bells and whistles.

Related Material

[pdf] [arXiv]
author = {Cheng, Bowen and Wei, Yunchao and Shi, Honghui and Feris, Rogerio and Xiong, Jinjun and Huang, Thomas},
title = {Revisiting RCNN: On Awakening the Classification Power of Faster RCNN},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}