Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with few-shot examples. However, this feature sharing mechanism inevitably causes semantic aliasing between novel classes when they have similar compositions of semantic concepts. In this paper, we reformulate few-shot segmentation as a semantic reconstruction problem, and convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. By introducing contrastive loss, we maximize the orthogonality of basis vectors while minimizing semantic aliasing between classes. Within the reconstructed representation space, we further suppress interference from other classes by projecting query features to the support vector for precise semantic activation. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems. Extensive experiments on PASCAL VOC and MS COCO datasets show that ASR achieves strong results compared with the prior works.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASR (ResNet-50) Mean IoU 33.85 # 65
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASR (ResNet-50) Mean IoU 35.75 # 65
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASR (ResNet-50) Mean IoU 58.16 # 79
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASR (VGG-16) Mean IoU 55.66 # 89
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASR (ResNet-50) Mean IoU 60.96 # 75
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASR (VGG-16) Mean IoU 57.99 # 81

Methods


No methods listed for this paper. Add relevant methods here