1 code implementation • 27 Mar 2024 • Run Shao, Zhaoyang Zhang, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li
Compared to Patch Embed, which requires more than one hundred tokens for one image, HOOK requires only 6 and 8 tokens for sparse and dense tasks, respectively, resulting in efficiency improvements of 1. 5 to 2. 8 times.
no code implementations • 26 Feb 2024 • Chao Tao, Dongsheng Kuang, Zhenyang Huang, Chengli Peng, Haifeng Li
To deal with this imbalance, we propose an equilibrium optimization loss function to regulate the optimization focus of the foreground and background, determine the hard case samples through the distribution of the loss values, and introduce dynamic weights in the loss term to gradually shift the optimization focus of the loss from the foreground to the background hard cases as the training progresses.
2 code implementations • 28 Jun 2023 • Zhaoyang Zhang, Zhen Ren, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li
Based on this, we propose contrastive learning with Gradient guided Sampling Strategy (GraSS) for RSI semantic segmentation.
no code implementations • 30 Jan 2021 • Chengli Peng, Jiayi Ma, Chen Chen, Xiaojie Guo
To verify the efficiency of the proposed bilateral attention decoder, we adopt a lightweight network as the backbone and compare our proposed method with other state-of-the-art real-time semantic segmentation methods on the Cityscapes and Camvid datasets.