Adaptively Marginalizing Cosine Logits for Effectively Learning Deep Visual Place Representation in Loop Closure Detection
- 22 November 2024
- book chapter
- Published by Springer Nature
- p. 15-31
Abstract
No abstract availableKeywords
This publication has 25 references indexed in Scilit:
- CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition2020
- AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations2019
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019
- CosFace: Large Margin Cosine Loss for Deep Face Recognition2018
- SphereFace: Deep Hypersphere Embedding for Face Recognition2017
- Deep Residual Learning for Image Recognition2016
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- SUN database: Large-scale scene recognition from abbey to zoo2010