%0 Generic %1 cheng2019segmentation %A Cheng, Zehua %A Wu, Yuxiang %A Xu, Zhenghua %A Lukasiewicz, Thomas %A Wang, Weiyang %D 2019 %K arch backbone detection loss segmentation %T Segmentation is All You Need %U http://arxiv.org/abs/1904.13300 %X Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under normal circumstances, their recall in a scene with extreme cases is unacceptably low. This is mainly because bounding box annotations contain much environment noise information, and non-maximum suppression (NMS) is required to select target boxes. Therefore, in this paper, we propose the first anchor-free and NMS-free object detection model called weakly supervised multimodal annotation segmentation (WSMA-Seg), which utilizes segmentation models to achieve an accurate and robust object detection without NMS. In WSMA-Seg, multimodal annotations are proposed to achieve an instance-aware segmentation using weakly supervised bounding boxes; we also develop a run-data-based following algorithm to trace contours of objects. In addition, we propose a multi-scale pooling segmentation (MSP-Seg) as the underlying segmentation model of WSMA-Seg to achieve a more accurate segmentation and to enhance the detection accuracy of WSMA-Seg. Experimental results on multiple datasets show that the proposed WSMA-Seg approach outperforms the state-of-the-art detectors.

@misc{cheng2019segmentation, abstract = {Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under normal circumstances, their recall in a scene with extreme cases is unacceptably low. This is mainly because bounding box annotations contain much environment noise information, and non-maximum suppression (NMS) is required to select target boxes. Therefore, in this paper, we propose the first anchor-free and NMS-free object detection model called weakly supervised multimodal annotation segmentation (WSMA-Seg), which utilizes segmentation models to achieve an accurate and robust object detection without NMS. In WSMA-Seg, multimodal annotations are proposed to achieve an instance-aware segmentation using weakly supervised bounding boxes; we also develop a run-data-based following algorithm to trace contours of objects. In addition, we propose a multi-scale pooling segmentation (MSP-Seg) as the underlying segmentation model of WSMA-Seg to achieve a more accurate segmentation and to enhance the detection accuracy of WSMA-Seg. Experimental results on multiple datasets show that the proposed WSMA-Seg approach outperforms the state-of-the-art detectors.}, added-at = {2019-06-23T22:38:19.000+0200}, author = {Cheng, Zehua and Wu, Yuxiang and Xu, Zhenghua and Lukasiewicz, Thomas and Wang, Weiyang}, biburl = {https://www.bibsonomy.org/bibtex/2463ee95f85666ec9a784be6ef366adcd/nmatsuk}, description = {Segmentation is All You Need}, interhash = {d0a13ce3b4a36e7abe2eafcfa413f049}, intrahash = {463ee95f85666ec9a784be6ef366adcd}, keywords = {arch backbone detection loss segmentation}, note = {cite arxiv:1904.13300Comment: 10 Pages}, timestamp = {2019-06-23T22:38:19.000+0200}, title = {Segmentation is All You Need}, url = {http://arxiv.org/abs/1904.13300}, year = 2019 }