HM: Hybrid Masking for Few-Shot Segmentation

We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Semantic Segmentation COCO-20i (1-shot) VAT (HM, ResNet-50) Mean IoU 43.2 # 35
FB-IoU 70 # 11
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-50) Mean IoU 44.3 # 28
FB-IoU 70.8 # 9
Few-Shot Semantic Segmentation COCO-20i (1-shot) HSNet (HM, ResNet-101) Mean IoU 46.5 # 17
FB-IoU 71.5 # 6
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-50) Mean IoU 44.7 # 27
FB-IoU 70.4 # 10
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASNet (HM, ResNet-101) Mean IoU 45.9 # 21
FB-IoU 71.1 # 7
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-50) Mean IoU 49.4 # 34
FB-IoU 72.2 # 17
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-50) Mean IoU 48.4 # 37
FB-IoU 72.2 # 17
Few-Shot Semantic Segmentation COCO-20i (5-shot) HSNet (HM, ResNet-101) Mean IoU 50.6 # 26
FB-IoU 72.9 # 13
Few-Shot Semantic Segmentation COCO-20i (5-shot) VAT (HM, ResNet-50) Mean IoU 48.3 # 38
FB-IoU 71.8 # 19
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASNet (HM, ResNet-101) Mean IoU 50.6 # 26
FB-IoU 73.3 # 9
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) HSNet (HM, ResNet-101) Mean IoU 66.5 # 6
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) VAT (HM, ResNet-50) Mean IoU 65.1 # 8
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) HSNet (HM, ResNet-50) Mean IoU 65.2 # 7
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) HSNet (HM, ResNet-50) Mean IoU 69.7 # 6
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) VAT (HM, ResNet-50) Mean IoU 69.7 # 6
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) HSNet (HM, ResNet-101) Mean IoU 70.9 # 5
Few-Shot Semantic Segmentation FSS-1000 (1-shot) VAT (HM, ResNet-101) Mean IoU 90.2 # 5
Few-Shot Semantic Segmentation FSS-1000 (1-shot) VAT (HM, ResNet-50) Mean IoU 89.4 # 9
Few-Shot Semantic Segmentation FSS-1000 (1-shot) HSNet (HM, ResNet-101) Mean IoU 87.8 # 13
Few-Shot Semantic Segmentation FSS-1000 (1-shot) HSNet (HM, ResNet-50) Mean IoU 87.1 # 15
Few-Shot Semantic Segmentation FSS-1000 (5-shot) HSNet (HM, ResNet-50) Mean IoU 88 # 15
Few-Shot Semantic Segmentation FSS-1000 (5-shot) HSNet (HM, ResNet-101) Mean IoU 88.5 # 13
Few-Shot Semantic Segmentation FSS-1000 (5-shot) VAT (HM, ResNet-50) Mean IoU 89.9 # 8
Few-Shot Semantic Segmentation FSS-1000 (5-shot) VAT (HM, ResNet-101) Mean IoU 90.5 # 6
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-50) Mean IoU 65 # 46
FB-IoU 76.5 # 33
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-101) Mean IoU 67.8 # 20
FB-IoU 79.4 # 10
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HSNet (HM, ResNet-101) Mean IoU 66.7 # 32
FB-IoU 77.8 # 23
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) VAT (HM, ResNet-50) Mean IoU 65.8 # 38
FB-IoU 77.1 # 30
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-50) Mean IoU 68.2 # 51
FB-IoU 78.5 # 30
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) VAT (HM, ResNet-101) Mean IoU 70.9 # 28
FB-IoU 81.5 # 16
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-101) Mean IoU 69.3 # 41
FB-IoU 79.7 # 28
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HSNet (HM, ResNet-50) Mean IoU 67.1 # 56
FB-IoU 77.7 # 34

Methods


No methods listed for this paper. Add relevant methods here