paper-with-me

홈 › Papers

DISK: Learning local features with policy gradient

2020-06-24 · NeurIPS 2020 12 · Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by leveraging principles from Reinforcement Learning (RL), optimizing end-to-end for a high number of correct feature matches. Our simple yet expressive probabilistic model lets us keep the training and inference regimes close, while maintaining good enough convergence properties to reliably train from scratch. Our features can be extracted very densely while remaining discriminative, challenging commonly held assumptions about what constitutes a good keypoint, as showcased in Fig. 1, and deliver state-of-the-art results on three public benchmarks.

📄 PDF Abstract BibTeX arXiv:2006.13566

Code (2)

cvlab-epfl/disk 공식 구현 pytorch
fabio-sim/LightGlue-ONNX pytorch

Tasks

Image Matchingreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecasting

2023-08-04 · Chetraj Pandey, Rafal A. Angryk, Manolis K. Georgoulis, Berkay Aydin

This paper presents a post hoc analysis of a deep learning-based full-disk solar flare prediction model. We used hourly full-disk line-of-sight magnetogram images and selected binary prediction mode to predict the occurr…

Data AugmentationSolar Flare Prediction

PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks

2021-11-30 · Shangjia Zhang, Zhaohuan Zhu, Mingon Kang

We developed Convolutional Neural Networks (CNNs) to rapidly and directly infer the planet mass from radio dust continuum images. Substructures induced by young planets in protoplanetary disks can be used to infer the po…

regression

Kinematic Evidence of an Embedded Protoplanet in HD 142666 Identified by Machine Learning

2023-01-12 · J. P. Terry, C. Hall, S. Abreau, S. Gleyzer

Observations of protoplanetary disks have shown that forming exoplanets leave characteristic imprints on the gas and dust of the disk. In the gas, these forming exoplanets cause deviations from Keplerian motion, which ca…

DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training

2024-05-08 · Renjie Liu, Yichuan Wang, Xiao Yan, Zhenkun Cai 외

Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, several systems store data on disk and condu…

CPUGraph Sampling

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction

2024-10-04 · Xinwei Zhang, Zhiqi Bu, Borja Balle, Mingyi Hong 외

Differential privacy (DP) offers a robust framework for safeguarding individual data privacy. To utilize DP in training modern machine learning models, differentially private optimizers have been widely used in recent ye…