Auto-Context R-CNN
share
Region-based convolutional neural networks (R-CNN) fast_rcnn,faster_rcnn,mask_rcnn have largely dominated object detection. Operators defined on RoIs (Region of Interests) play an important role in R-CNNs such as RoIPooling fast_rcnn and RoIAlign mask_rcnn. They all only utilize information inside RoIs for RoI prediction, even with their recent deformable extensions deformable_cnn. Although surrounding context is well-known for its importance in object detection, it has yet been integrated in R-CNNs in a flexible and effective way. Inspired by the auto-context work auto_context and the multi-class object layout work nms_context, this paper presents a generic context-mining RoI operator (i.e., RoICtxMining) seamlessly integrated in R-CNNs, and the resulting object detection system is termed Auto-Context R-CNN which is trained end-to-end. The proposed RoICtxMining operator is a simple yet effective two-layer extension of the RoIPooling or RoIAlign operator. Centered at an object-RoI, it creates a 3× 3 layout to mine contextual information adaptively in the 8 surrounding context regions on-the-fly. Within each of the 8 context regions, a context-RoI is mined in term of discriminative power and its RoIPooling / RoIAlign features are concatenated with the object-RoI for final prediction. The proposed Auto-Context R-CNN is robust to occlusion and small objects, and shows promising vulnerability for adversarial attacks without being adversarially-trained. In experiments, it is evaluated using RoIPooling as the backbone and shows competitive results on Pascal VOC, Microsoft COCO, and KITTI datasets (including 6.9% mAP improvements over the R-FCN rfcn method on COCO test-dev dataset and the first place on both KITTI pedestrian and cyclist detection as of this submission).
READ FULL TEXT
