2 papers
cs.CV2024
MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation
Shenwang Jiang, Jianan Li, Ying Wang +4
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previou…
cs.LG2022
Dynamic Loss For Robust Learning
Shenwang Jiang, Jianan Li, Jizhou Zhang +2
Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperfor…