1 code implementation • 25 Mar 2024 • Dongwei Gan, Ming Chang, Juan Chen
Our encoder uses capsule blocks and EfficientViT blocks to jointly capture local and global semantic information more effectively and efficiently with less information loss, while the decoder employs CNN blocks and EfficientViT blocks to catch ffner details for segmentation.
1 code implementation • NeurIPS 2021 • Zhixing Du, Rui Zhang, Ming Chang, Xishan Zhang, Shaoli Liu, Tianshi Chen, Yunji Chen
Second, these methods imitate some features which are mistakenly regarded as the background by the teacher detector.