Deng Cai
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
Neural Information Processing Systems http://nips.cc/
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
Neural Information Processing Systems http://nips.cc/
Region Mutual Information Loss for Semantic Segmentation
Shuai Zhao, Yang Wang, Zheng Yang, Deng Cai
Neural Information Processing Systems http://nips.cc/
Region Mutual Information Loss for Semantic Segmentation
Shuai Zhao, Yang Wang, Zheng Yang, Deng Cai
Semantic segmentation is a fundamental problem in computer vision. It is considered as a pixel-wise classification problem in practice, and most segmentation models use a pixel-wise loss as their optimization criterion. However, the pixelwise loss ignores the dependencies between pixels in an image. Several ways to exploit the relationship between pixels have been investigated, e.g., conditional random fields (CRF) and pixel affinity based methods. Nevertheless, these methods usually require additional model branches, large extra memories, or more inference time.