The Self-Optimal-Transport Feature Transform

04/06/2022
by   Daniel Shalam, et al.
0

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.

READ FULL TEXT

page 8

page 20

page 21

research
02/10/2020

CO-Optimal Transport

Optimal transport (OT) is a powerful geometric and probabilistic tool fo...
research
04/18/2023

Sliced Optimal Transport on the Sphere

Sliced optimal transport reduces optimal transport on multi-dimensional ...
research
11/02/2022

Entropic Neural Optimal Transport via Diffusion Processes

We propose a novel neural algorithm for the fundamental problem of compu...
research
05/17/2017

Co-clustering through Optimal Transport

In this paper, we present a novel method for co-clustering, an unsupervi...
research
05/27/2020

Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport

Selecting input features of top relevance has become a popular method fo...
research
07/02/2021

Data-driven mapping between functional connectomes using optimal transport

Functional connectomes derived from functional magnetic resonance imagin...
research
10/05/2022

Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics

Measuring Sentence Textual Similarity (STS) is a classic task that can b...

Please sign up or login with your details

Forgot password? Click here to reset