ECCV 2020:那些你可能会感兴趣的 paper

技术讨论 你找不到我 ⋅ 于 9个月前 ⋅ 1888 阅读
文章来源:千佛山彭于晏@知乎
  • 本文内容摘录自ECCV 2020 Accepted Papers Website。
  • 目前多数的paper还没有放出来,敬请期待。

Accepted Papers | ECCV 2020​eccv2020


Image Recognition 相关

  • Learning and aggregating deep local descriptors for instance-level recognition (Oral)
  • Online Invariance Selection for Local Feature Descriptors(Oral)
  • Hybrid Models for Open Set Recognition(Oral)
  • Learning to Balance Specificity and Invariance for In and Out of Domain Generalization


Few-shot Learning 相关

  • Prototype Rectification for Few-Shot Learning (Oral)
  • Negative Margin Matters: Understanding Margin in Few-shot Classification(Spotlight)
  • Associative Alignment for Few-shot Image Classification(Spotlight)
  • TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification
  • When Does Self-supervision Improve Few-shot Learning?
  • Rethinking few-shot image classification: a good embedding is all you need?


Person Re-ID 相关

  • Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (Oral)
  • Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
  • Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
  • Faster Person Re-Identification


Face 相关

  • Semi-Siamese Training for Shallow Face Learning(Spotlight)
  • BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
  • Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
  • RAN: Resolution Adaption Network for Low-resolution Face Recognition


Long-Tail 相关

  • Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets(Spotlight)
  • Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification(Spotlight)
  • Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
  • The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation
  • Feature Space Augmentation for Long-Tailed Data


Representation Learning 相关

  • Big Transfer (BiT): General Visual Representation Learning (Spotlight)


Metric Learning 相关

  • Metric learning: cross-entropy vs. pairwise losses (Spotlight)
  • The Group Loss for Deep Metric Learning
  • DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
  • Spherical Feature Transform for Deep Metric Learning
  • ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
  • A Metric Learning Reality Check
  • A Simple and Effective Framework for Pairwise Deep Metric Learning
  • Hard negatives examples are hard, but useful


Retrieval 相关

  • Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval


相关推荐:

ECCV 2020 Oral 论文汇总!

ECCV 2020 接受论文汇总

微信公众号: 极市平台(ID: extrememart )
每天推送最新CV干货

成为第一个点赞的人吧 :bowtie:
回复数量: 0
暂无回复~
您需要登陆以后才能留下评论!