Papers › Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
Yuanwei Liu, Nian Liu, Xiwen Yao, Junwei Han
Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective category information from the support to match with the corresponding objects in query. However, they all ignored the category information gap between query and support images. If the objects in them show large intra-class diversity, forcibly migrating the category information from the support to the query is ineffective. To solve this problem, we are the first to introduce an intermediate prototype for mining both deterministic category information from the support and adaptive category knowledge from the query. Specifically, we design an Intermediate Prototype Mining Transformer (IPMT) to learn the prototype in an iterative way. In each IPMT layer, we propagate the object information in both support and query features to the prototype and then use it to activate the query feature map. By conducting this process iteratively, both the intermediate prototype and the query feature can be progressively improved. At last, the final query feature is used to yield precise segmentation prediction. Extensive experiments on both PASCAL-5i and COCO-20i datasets clearly verify the effectiveness of our IPMT and show that it outperforms previous state-of-the-art methods by a large margin. Code is available at https://github.com/LIUYUANWEI98/IPMT
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.06780")
Code
Syntology Ran 6 of 13 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 3 ran with no contract checked.
By repository: official repository: 13 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
13 samples harvested; 6 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from LIUYUANWEI98/IPMT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
df77cb77dfe58d6d · report
1dad93b61e98c32e · report
2a80220dabcb742a · report
600ff2c45e0de056 · report
2a66f4ab6863908c · report
0684a938c70bf564 · report
136834d66336e6b9 · report
277a13798d6d6981 · report
cbfcdd76ffcf2a11 · report
643408ce821a11cf · report
b925dc5fd8492c34 · report
dc824689b4f991cf · report
4708c105ce1b6276 · report
Tasks
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) | IPMT (ResNet-50) | Mean IoU | 43 | #47 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | IPMT (ResNet-101) | Mean IoU | 42.6 | #48 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | IPMT (ResNet-101) | Mean IoU | 47.9 | #53 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | IPMT (ResNet-50) | Mean IoU | 47.5 | #55 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | IPMT (ResNet-50) | FB-IoU | 77.1 | #35 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | IPMT (ResNet-50) | Mean IoU | 66.8 | #35 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | IPMT (ResNet-101) | FB-IoU | 78.5 | #41 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | IPMT (ResNet-101) | Mean IoU | 66.1 | #41 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | IPMT (ResNet-101) | FB-IoU | 80.3 | #51 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | IPMT (ResNet-101) | Mean IoU | 69.2 | #51 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | IPMT (ResNet-50) | FB-IoU | 81.4 | #58 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | IPMT (ResNet-50) | Mean IoU | 68.2 | #58 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