Papers › The Self-Optimal-Transport Feature Transform

The Self-Optimal-Transport Feature Transform

6 Apr 2022arXiv:2204.03065archive 2025-07-28

Daniel Shalam, Simon Korman

The Self-Optimal-Transport (SOT) feature transform is designed to upgrade the set of features of a data instance to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order relations between the instance features. Distances between transformed features capture their direct original similarity and their third party agreement regarding similarity to other features in the set. A particular min-cost-max-flow fractional matching problem, whose entropy regularized version can be approximated by an optimal transport (OT) optimization, results in our transductive transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. Empirically, the transform is highly effective and flexible in its use, consistently improving networks it is inserted into, in a variety of tasks and training schemes. We demonstrate its merits through the problem of unsupervised clustering and its efficiency and wide applicability for few-shot-classification, with state-of-the-art results, and large-scale person re-identification.

PaperPDFCode

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

Code

danielshalam/bpa officialpytorch 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

Few-Shot Image ClassificationLarge-Scale Person Re-IdentificationPerson Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) PT+MAP+SF+SOT (transductive) Accuracy 89.94 #1 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) PT+MAP+SF+SOT (transductive) Accuracy 92.83 #2 of 39 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 1-shot PT+MAP+SF+SOT (transductive) Accuracy 95.80 #1 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot PT+MAP+SF+SOT (transductive) Accuracy 97.12 #2 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) PT+MAP+SF+SOT (transductive) Accuracy 85.59 #5 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) PT+MAP+SF+SOT (transductive) Accuracy 91.34 #8 of 95 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.

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