Semi-supervised Learning of Pushforwards For Domain Translation & Adaptation

• URL: http://arxiv.org/abs/2304.08673v1
• Date: Tue, 18 Apr 2023 00:35:32 GMT
• Title: Semi-supervised Learning of Pushforwards For Domain Translation & Adaptation
• Authors: Nishant Panda, Natalie Klein, Dominic Yang, Patrick Gasda and Diane Oyen
• Abstract summary: Given two probability densities on related data spaces, we seek a map pushing one density to the other. For maps to have utility in a broad application space, the map must be available to apply on out-of-sample data points. We introduce a novel pushforward map learning algorithm that utilizes normalizing flows to parameterize the map.
• Score: 3.800498098285222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given two probability densities on related data spaces, we seek a map pushing one density to the other while satisfying application-dependent constraints. For maps to have utility in a broad application space (including domain translation, domain adaptation, and generative modeling), the map must be available to apply on out-of-sample data points and should correspond to a probabilistic model over the two spaces. Unfortunately, existing approaches, which are primarily based on optimal transport, do not address these needs. In this paper, we introduce a novel pushforward map learning algorithm that utilizes normalizing flows to parameterize the map. We first re-formulate the classical optimal transport problem to be map-focused and propose a learning algorithm to select from all possible maps under the constraint that the map minimizes a probability distance and application-specific regularizers; thus, our method can be seen as solving a modified optimal transport problem. Once the map is learned, it can be used to map samples from a source domain to a target domain. In addition, because the map is parameterized as a composition of normalizing flows, it models the empirical distributions over the two data spaces and allows both sampling and likelihood evaluation for both data sets. We compare our method (parOT) to related optimal transport approaches in the context of domain adaptation and domain translation on benchmark data sets. Finally, to illustrate the impact of our work on applied problems, we apply parOT to a real scientific application: spectral calibration for high-dimensional measurements from two vastly different environments

Related papers

• Efficient Map Sparsification Based on 2D and 3D Discretized Grids [47.22997560184043]
  As a map grows larger, more memory is required and localization becomes inefficient. Previous map sparsification methods add a quadratic term in mixed-integer programming to enforce a uniform distribution of selected landmarks. In this paper, we formulate map sparsification in an efficient linear form and select uniformly distributed landmarks based on 2D discretized grids.
  arXiv  Detail & Related papers  (2023-03-20T05:49:14Z)
• Unpaired Image Super-Resolution with Optimal Transport Maps [128.1189695209663]
  Real-world image super-resolution (SR) tasks often do not have paired datasets limiting the application of supervised techniques. We propose an algorithm for unpaired SR which learns an unbiased OT map for the perceptual transport cost. Our algorithm provides nearly state-of-the-art performance on the large-scale unpaired AIM-19 dataset.
  arXiv  Detail & Related papers  (2022-02-02T16:21:20Z)
• Near-optimal estimation of smooth transport maps with kernel sums-of-squares [81.02564078640275]
  Under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. The object of interest for applications such as generative modeling is the underlying optimal transport map. We propose the first tractable algorithm for which the statistical $L2$ error on the maps nearly matches the existing minimax lower-bounds for smooth map estimation.
  arXiv  Detail & Related papers  (2021-12-03T13:45:36Z)
• Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach [6.510061176722248]
  In many trajectory-based applications, it is necessary to map raw GPS trajectories onto road networks in digital maps. In this paper, we consider the map-matching task from the data perspective, proposing a deep learning-based map-matching model. We generate synthetic trajectory data to pre-train the Transformer model and then fine-tune the model with a limited number of ground-truth data.
  arXiv  Detail & Related papers  (2021-08-01T11:51:11Z)
• Scalable Computation of Monge Maps with General Costs [12.273462158073302]
  Monge map refers to the optimal transport map between two probability distributions. We present a scalable algorithm for computing the Monge map between two probability distributions.
  arXiv  Detail & Related papers  (2021-06-07T17:23:24Z)
• ICON: Learning Regular Maps Through Inverse Consistency [19.27928605302463]
  We explore what induces regularity for spatial transformations, e.g., when computing image registrations. We find that deep networks combined with an inverse consistency loss and randomized off-grid yield well behaved, approximately diffeomorphic, spatial transformations. Despite the simplicity of this approach, our experiments present compelling evidence, on both synthetic and real data, that regular maps can be obtained without carefully tuned explicit regularizers and competitive registration performance.
  arXiv  Detail & Related papers  (2021-05-10T15:52:12Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• Learning to Match Distributions for Domain Adaptation [116.14838935146004]
  This paper proposes Learning to Match (L2M) to automatically learn the cross-domain distribution matching. L2M reduces the inductive bias by using a meta-network to learn the distribution matching loss in a data-driven way. Experiments on public datasets substantiate the superiority of L2M over SOTA methods.
  arXiv  Detail & Related papers  (2020-07-17T03:26:13Z)
• Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps [78.2581910688094]
  This work introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC.
  arXiv  Detail & Related papers  (2020-06-09T12:35:55Z)

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.