Feature-Proxy Transformer for Few-Shot Segmentation

13 Oct 2022  ·  Jian-Wei Zhang, Yifan Sun, Yi Yang, Wei Chen ·

Few-shot segmentation (FSS) aims at performing semantic segmentation on novel classes given a few annotated support samples. With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head. Due to the intricacy of the decoder and its matching pipeline, it is not easy to follow such an FSS framework. This paper revives the straightforward framework of "feature extractor $+$ linear classification head" and proposes a novel Feature-Proxy Transformer (FPTrans) method, in which the "proxy" is the vector representing a semantic class in the linear classification head. FPTrans has two keypoints for learning discriminative features and representative proxies: 1) To better utilize the limited support samples, the feature extractor makes the query interact with the support features from the bottom to top layers using a novel prompting strategy. 2) FPTrans uses multiple local background proxies (instead of a single one) because the background is not homogeneous and may contain some novel foreground regions. These two keypoints are easily integrated into the vision transformer backbone with the prompting mechanism in the transformer. Given the learned features and proxies, FPTrans directly compares their cosine similarity for segmentation. Although the framework is straightforward, we show that FPTrans achieves competitive FSS accuracy on par with state-of-the-art decoder-based methods.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Semantic Segmentation COCO-20i (1-shot) FPTrans (ViT-B/16) Mean IoU 42 # 43
Few-Shot Semantic Segmentation COCO-20i (1-shot) FPTrans (DeiT-B/16) Mean IoU 47 # 12
Few-Shot Semantic Segmentation COCO-20i (5-shot) FPTrans (ViT-B/16) Mean IoU 53.8 # 15
Few-Shot Semantic Segmentation COCO-20i (5-shot) FPTrans (DeiT-B/16) Mean IoU 58.9 # 3
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) FPTrans (DeiT-B/16) Mean IoU 69.7 # 2
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) FPTrans (ViT-B/16) Mean IoU 67.6 # 5
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) FPTrans (DeiT-B/16) Mean IoU 79.3 # 1
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) FPTrans (ViT-B/16) Mean IoU 76.9 # 4
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) FPTrans (DeiT-B/16) Mean IoU 68.8 # 13
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) FPTrans (ViT-B/16) Mean IoU 64.7 # 49
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) FPTrans (DeiT-B/16) Mean IoU 78 # 3
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) FPTrans (ViT-B/16) Mean IoU 73.7 # 9

Methods