Papers › MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic...
MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation
Yong Yang, Qiong Chen, Yuan Feng, Tianlin Huang
Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set. However, the extracted knowledge is insufficient to cope with the variable intra-class differences since the knowledge is obtained from a few samples in the support set. To address the problem, we propose a multi-information aggregation network (MIANet) that effectively leverages the general knowledge, i.e., semantic word embeddings, and instance information for accurate segmentation. Specifically, in MIANet, a general information module (GIM) is proposed to extract a general class prototype from word embeddings as a supplement to instance information. To this end, we design a triplet loss that treats the general class prototype as an anchor and samples positive-negative pairs from local features in the support set. The calculated triplet loss can transfer semantic similarities among language identities from a word embedding space to a visual representation space. To alleviate the model biasing towards the seen training classes and to obtain multi-scale information, we then introduce a non-parametric hierarchical prior module (HPM) to generate unbiased instance-level information via calculating the pixel-level similarity between the support and query image features. Finally, an information fusion module (IFM) combines the general and instance information to make predictions for the query image. Extensive experiments on PASCAL-5i and COCO-20i show that MIANet yields superior performance and set a new state-of-the-art. Code is available at https://github.com/Aldrich2y/MIANet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | MIANet (ResNet-50) | FB-IoU | 71.51 | #18 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | MIANet (ResNet-50) | Mean IoU | 47.66 | #18 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | MIANet (VGG-16) | FB-IoU | 71.01 | #33 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | MIANet (VGG-16) | Mean IoU | 45.69 | #33 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | MIANet (ResNet-50) | FB-IoU | 73.13 | #30 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | MIANet (ResNet-50) | Mean IoU | 51.65 | #30 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | MIANet (VGG-16) | FB-IoU | 73.81 | #34 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | MIANet (VGG-16) | Mean IoU | 51.03 | #34 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MIANet (ResNet-50) | FB-IoU | 79.54 | #17 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MIANet (ResNet-50) | Mean IoU | 68.72 | #17 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MIANet (ResNet-101) | Mean IoU | 67.63 | #24 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MIANet (VGG-16) | FB-IoU | 79.22 | #30 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MIANet (VGG-16) | Mean IoU | 67.10 | #30 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MIANet (VGG-16) | FB-IoU | 82.69 | #20 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MIANet (VGG-16) | Mean IoU | 71.99 | #20 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MIANet (ResNet-50) | FB-IoU | 82.2 | #25 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MIANet (ResNet-50) | Mean IoU | 71.59 | #25 of 96 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections