paper-with-me

홈 › Papers

Normalized Matching Transformer

2025-03-22 · Abtin Pourhadi, Paul Swoboda

We present a new state of the art approach for sparse keypoint matching between pairs of images. Our method consists of a fully deep learning based approach combining a visual backbone coupled with a SplineCNN graph neural network for feature processing and a normalized transformer decoder for decoding keypoint correspondences together with the Sinkhorn algorithm. Our method is trained using a contrastive and a hyperspherical loss for better feature representations. We additionally use data augmentation during training. This comparatively simple architecture combining extensive normalization and advanced losses outperforms current state of the art approaches on PascalVOC and SPair-71k datasets by $5.1\%$ and $2.2\%$ respectively compared to BBGM, ASAR, COMMON and GMTR while training for at least $1.7x$ fewer epochs.

📄 PDF Abstract BibTeX arXiv:2503.17715

Code (1)

apollos1301/normmatchtrans 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Improving Address Matching using Siamese Transformer Networks

2023-07-05 · André V. Duarte, Arlindo L. Oliveira

Matching addresses is a critical task for companies and post offices involved in the processing and delivery of packages. The ramifications of incorrectly delivering a package to the wrong recipient are numerous, ranging…

GPU

Information criteria for non-normalized models

2019-05-15 · Takeru Matsuda, Masatoshi Uehara, Aapo Hyvarinen

Many statistical models are given in the form of non-normalized densities with an intractable normalization constant. Since maximum likelihood estimation is computationally intensive for these models, several estimation …

Model Selection

Bregman divergence as general framework to estimate unnormalized statistical models

2012-02-14 · Michael Gutmann, Jun-Ichiro Hirayama

We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. W…

Momentum Improves Normalized SGD

2020-02-09 · ICML 2020 1 · Ashok Cutkosky, Harsh Mehta

We provide an improved analysis of normalized SGD showing that adding momentum provably removes the need for large batch sizes on non-convex objectives. Then, we consider the case of objectives with bounded second deriva…

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

2020-02-18 · pproximateinference AABI Symposium 2019 12 · Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu 외

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation…