Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection

October 05, 2018 ยท Entered Twilight ยท ๐Ÿ› arXiv.org

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 5.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, ThirdPartyNotices.txt, demo, experiments, faster_rcnn, faster_rcnn_dcr, fpn, fpn_dcr, init.bat, init.sh, lib, requirements.txt

Authors Bowen Cheng, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas Huang, Humphrey Shi arXiv ID 1810.04002 Category cs.CV: Computer Vision Citations 49 Venue arXiv.org Repository https://github.com/bowenc0221/Decoupled-Classification-Refinement โญ 169 Last Checked 1 month ago
Abstract
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 and they have a large negative impact on the performance of object detectors. We conjecture there are three factors: (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. In particular, DCR places a separate classification network in parallel with the localization network (base detector). With ROI Pooling placed on the early stage of the classification network, we enforce an adaptive receptive field in DCR. During training, DCR samples hard false positives from the base detector and trains a strong classifier to refine classification results. During testing, DCR refines all boxes from the base detector. Experiments show competitive results on PASCAL VOC and COCO without any bells and whistles. Our codes are available at: https://github.com/bowenc0221/Decoupled-Classification-Refinement.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision