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?
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.
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
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) | 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
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