The Self-Optimal-Transport Feature Transform

• URL: http://arxiv.org/abs/2204.03065v1
• Date: Wed, 6 Apr 2022 20:00:39 GMT
• Title: The Self-Optimal-Transport Feature Transform
• Authors: Daniel Shalam and Simon Korman
• Abstract summary: We show how to upgrade the set of features of a data instance to facilitate downstream matching or grouping related tasks. 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. Empirically, the transform is highly effective and flexible in its use, consistently improving networks it is inserted into.
• Score: 2.804721532913997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Transfer Learning of Surrogate Models: Integrating Domain Warping and Affine Transformations [4.515998639772672]
  Surrogate models provide efficient alternatives to computationally demanding real-world processes. Previous studies have investigated the transfer of differentiable and non-differentiable surrogate models. This paper extends previous research by addressing a broader range of transformations.
  arXiv  Detail & Related papers  (2025-01-30T13:46:48Z)
• Self-supervised Transformation Learning for Equivariant Representations [26.207358743969277]
  Unsupervised representation learning has significantly advanced various machine learning tasks. We propose Self-supervised Transformation Learning (STL), replacing transformation labels with transformation representations derived from image pairs. We demonstrate the approach's effectiveness across diverse classification and detection tasks, outperforming existing methods in 7 out of 11 benchmarks.
  arXiv  Detail & Related papers  (2025-01-15T10:54:21Z)
• Structural Entropy Guided Probabilistic Coding [52.01765333755793]
  We propose a novel structural entropy-guided probabilistic coding model, named SEPC. We incorporate the relationship between latent variables into the optimization by proposing a structural entropy regularization loss. Experimental results across 12 natural language understanding tasks, including both classification and regression tasks, demonstrate the superior performance of SEPC.
  arXiv  Detail & Related papers  (2024-12-12T00:37:53Z)
• Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations [75.14793516745374]
  We propose to strengthen the structural inductive bias of a Transformer by intermediate pre-training. Our experiments confirm that this helps with few-shot learning of syntactic tasks such as chunking. Our analysis shows that the intermediate pre-training leads to attention heads that keep track of which syntactic transformation needs to be applied to which token.
  arXiv  Detail & Related papers  (2024-07-05T14:29:44Z)
• The Balanced-Pairwise-Affinities Feature Transform [2.3020018305241337]
  TheBPA feature transform is designed to upgrade the features of a set of input items to facilitate downstream matching or grouping related tasks. A particular min-cost-max-flow fractional matching problem leads to a transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. Empirically, the transform is highly effective and flexible in its use and consistently improves networks it is inserted into, in a variety of tasks and training schemes.
  arXiv  Detail & Related papers  (2024-06-25T14:28:05Z)
• Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence [51.54175067684008]
  This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. We first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.
  arXiv  Detail & Related papers  (2024-03-17T07:02:55Z)
• Deep Neural Networks with Efficient Guaranteed Invariances [77.99182201815763]
  We address the problem of improving the performance and in particular the sample complexity of deep neural networks. Group-equivariant convolutions are a popular approach to obtain equivariant representations. We propose a multi-stream architecture, where each stream is invariant to a different transformation.
  arXiv  Detail & Related papers  (2023-03-02T20:44:45Z)
• ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement [80.94378602238432]
  We propose an efficient structure named Correspondence Efficient Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner. To achieve this, multiple transformer blocks are stage-wisely connected to gradually refine the predicted coordinates. Experiments on various sparse and dense matching tasks demonstrate the superiority of our method in both efficiency and effectiveness against existing state-of-the-arts.
  arXiv  Detail & Related papers  (2022-09-25T13:05:33Z)
• A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks [44.739573338273175]
  We propose a multi-transformation evolutionary framework for influence transformation (MTEFIM) to exploit potential similarities and unique advantages of alternate transformations. MTEFIM can efficiently utilize the potentially transferable knowledge across multiple transformations to achieve highly competitive performance. The MTEFIM is validated on four real-world social networks.
  arXiv  Detail & Related papers  (2022-04-07T08:53:42Z)
• Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
  Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-15T06:52:25Z)
• Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization [8.37077056358265]
  We propose a new computational primitive for building invariant networks based instead on optimization. We provide empirical and theoretical corroboration of the efficiency gains and soundness of our proposed method. We demonstrate its utility in constructing an efficient invariant network for a simple hierarchical object detection task.
  arXiv  Detail & Related papers  (2022-03-09T19:04:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.