Papers › Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

11 Dec 2020CVPR 2021 1arXiv:2012.06166archive 2025-07-28

Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud, Pablo Piantanida, Ismail Ben Ayed, Jose Dolz

We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm. We introduce a transductive inference for a given query image, leveraging the statistics of its unlabeled pixels, by optimizing a new loss containing three complementary terms: i) the cross-entropy on the labeled support pixels; ii) the Shannon entropy of the posteriors on the unlabeled query-image pixels; and iii) a global KL-divergence regularizer based on the proportion of the predicted foreground. As our inference uses a simple linear classifier of the extracted features, its computational load is comparable to inductive inference and can be used on top of any base training. Foregoing episodic training and using only standard cross-entropy training on the base classes, our inference yields competitive performances on standard benchmarks in the 1-shot scenarios. As the number of available shots increases, the gap in performances widens: on PASCAL-5i, our method brings about 5% and 6% improvements over the state-of-the-art, in the 5- and 10-shot scenarios, respectively. Furthermore, we introduce a new setting that includes domain shifts, where the base and novel classes are drawn from different datasets. Our method achieves the best performances in this more realistic setting. Our code is freely available online: https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mboudiaf/RePRI-for-Few-Shot-Segmentation officialmentioned in papermentioned on GitHubpytorch report
Bingolby/medical_few_shot_segmentation mentioned on GitHubpytorch report

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

AllFew-Shot Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) RePRI (ResNet-50) Mean IoU 34.1 #76 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (10-shot) RePRI (ResNet-50) Mean IoU 44.1 #3 of 4 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) RePRI (ResNet-50) Mean IoU 41.6 #69 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (1-shot) RePRI (ResNet-50) Mean IoU 63.1 #11 of 13 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i -> Pascal VOC (5-shot) RePRI (ResNet-50) Mean IoU 67.7 #10 of 12 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) RePRI (ResNet-50) Mean IoU 59.7 #84 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) RePRI (ResNet-101) Mean IoU 59.4 #85 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (10-Shot) RePRI (ResNet-50) Mean IoU 68.1 #3 of 4 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) RePRI (ResNet-50) Mean IoU 66.6 #68 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) RePRI (ResNet-101) Mean IoU 65.6 #73 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

Transductive Inference

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