paper-with-me

Papers

Automatic Target Recognition Using Discrimination Based on Optimal Transport

2019-04-06 · Ali Sadeghian, Deoksu Lim, Johan Karlsson, Jian Li

The use of distances based on optimal transportation has recently shown promise for discrimination of power spectra. In particular, spectral estimation methods based on l1 regularization as well as covariance based methods can be shown to be robust with respect to such distances. These transportation distances provide a geometric framework where geodesics corresponds to smooth transition of spectral mass, and have been useful for tracking. In this paper, we investigate the use of these distances for automatic target recognition. We study the use of the Monge-Kantorovich distance compared to the standard l2 distance for classifying civilian vehicles based on SAR images. We use a version of the Monge-Kantorovich distance that applies also for the case where the spectra may have different total mass, and we formulate the optimization problem as a minimum flow problem that can be computed using efficient algorithms.

📄 PDF Abstract BibTeX arXiv:1904.03534

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

L1 Regularization $L_{1}$ Regularization is a regularization technique applied to the weights of a neural network. We minimize a loss function compromising both the primary loss function and a…

Similar Papers 제목 키워드 기반

Wasserstein Barycenter for Multi-Source Domain Adaptation

2021-06-19 · CVPR 2021 1 · Eduardo Fernandes Montesuma, Fred Maurice Ngole Mboula

Multi-source domain adaptation is a key technique that allows a model to be trained on data coming from various probability distribution. To overcome the challenges posed by this learning scenario, we propose a metho…

Domain AdaptationFace RecognitionMulti-Source Unsupervised Domain AdaptationMusic Genre Recognition+2

Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans

2026-01-19 · Abdel Djalil Sad Saoud, Fred Maurice Ngolè Mboula, Hanane Slimani arxiv

Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain alignment, such…

Unsupervised Domain AdaptationMusic Genre Recognition

Unified Optimal Transport Framework for Universal Domain Adaptation

2022-10-31 · Wanxing Chang, Ye Shi, Hoang Duong Tuan, Jingya Wang

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Since both domains may hold private classes, identifying target common samples…

Domain AdaptationRepresentation LearningUniversal Domain Adaptation

OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition

2023-06-05 · Li Fu, Siqi Li, Qingtao Li, Fangzhu Li 외

Self-Supervised Learning (SSL) Automatic Speech Recognition (ASR) models have shown great promise over Supervised Learning (SL) ones in low-resource settings. However, the advantages of SSL are gradually weakened when th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognition+1

MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition

2023-02-22 · Jiaming Zhou, Shiwan Zhao, Ning Jiang, Guoqing Zhao 외

End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unl…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Cross-environment ASRDomain Adaptation+3