Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
This work addresses the challenge of reducing labeling costs in semantic segmentation for computer vision applications, representing an incremental improvement by combining elements from existing multi-stage and single-stage methods.
The paper tackles the problem of weakly supervised semantic segmentation by embedding affinity learning from multi-stage approaches into a single-stage model, using an adaptive affinity loss and a label reassign loss to mitigate errors in pseudo labels, achieving performance that outperforms standard single-stage methods and is comparable to multi-stage methods on the PASCAL VOC 2012 dataset.
Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS), including single- and multi-stage process, has attracted large attention due to data labeling efficiency. In this paper, we propose to embed affinity learning of multi-stage approaches in a single-stage model. To be specific, we introduce an adaptive affinity loss to thoroughly learn the local pairwise affinity. As such, a deep neural network is used to deliver comprehensive semantic information in the training phase, whilst improving the performance of the final prediction module. On the other hand, considering the existence of errors in the pseudo labels, we propose a novel label reassign loss to mitigate over-fitting. Extensive experiments are conducted on the PASCAL VOC 2012 dataset to evaluate the effectiveness of our proposed approach that outperforms other standard single-stage methods and achieves comparable performance against several multi-stage methods.