paper-with-me

Papers

VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization

2023-07-31 · Jiuhong Xiao, Gao Zhu, Giuseppe Loianno

Visual Geo-localization (VG) is a critical research area for identifying geo-locations from visual inputs, particularly in autonomous navigation for robotics and vehicles. Current VG methods often learn feature extractors from geo-labeled images to create dense, geographically relevant representations. Recent advances in Self-Supervised Learning (SSL) have demonstrated its capability to achieve performance on par with supervised techniques with unlabeled images. This study presents a novel VG-SSL framework, designed for versatile integration and benchmarking of diverse SSL methods for representation learning in VG, featuring a unique geo-related pair strategy, GeoPair. Through extensive performance analysis, we adapt SSL techniques to improve VG on datasets from hand-held and car-mounted cameras used in robotics and autonomous vehicles. Our results show that contrastive learning and information maximization methods yield superior geo-specific representation quality, matching or surpassing the performance of state-of-the-art VG techniques. To our knowledge, This is the first benchmarking study of SSL in VG, highlighting its potential in enhancing geo-specific visual representations for robotics and autonomous vehicles. The code is publicly available at https://github.com/arplaboratory/VG-SSL.

📄 PDF Abstract BibTeX arXiv:2308.00090

Code (1)

arplaboratory/vg_ssl 공식 구현 pytorch

Tasks

Autonomous NavigationAutonomous VehiclesBenchmarkingContrastive Learninggeo-localizationRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Residual Connection 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
ColorJitter 설명 없음
Kaiming Initialization 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Random Resized Crop 설명 없음

Similar Papers 제목 키워드 기반

Scaling and Benchmarking Self-Supervised Visual Representation Learning

2019-05-03 · ICCV 2019 10 · Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount…

Benchmarkingobject-detectionObject DetectionReinforcement Learning+4

Benchmarking Representation Learning for Natural World Image Collections

2021-03-30 · CVPR 2021 1 · Grant van Horn, Elijah Cole, Sara Beery, Kimberly Wilber 외

Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring any explicit label supervision. However, to date the vast ma…

BenchmarkingBinary ClassificationClassificationFine-Grained Visual Categorization+4

Self-Supervised Speech Representation Learning: A Review

2022-05-21 · Abdelrahman Mohamed, Hung-Yi Lee, Lasse Borgholt, Jakob D. Havtorn 외

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)BenchmarkingRepresentation Learning+3

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?

2023-06-01 · Salah Zaiem, Youcef Kemiche, Titouan Parcollet, Slim Essid 외

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts of annotated data. The high number of pro…

BenchmarkingDecoderSelf-Supervised Learning

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads

2023-08-28 · Salah Zaiem, Youcef Kemiche, Titouan Parcollet, Slim Essid 외

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of compreh…

BenchmarkingSelf-Supervised Learning