咨询与建议

限定检索结果

文献类型

  • 2 篇 会议

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 计算机科学与技术...

主题

  • 2 篇 continual learni...
  • 2 篇 class incrementa...
  • 2 篇 incremental lear...
  • 1 篇 object detection
  • 1 篇 ciod
  • 1 篇 pseudo labeling
  • 1 篇 stable diffusion
  • 1 篇 replay
  • 1 篇 vision-language ...
  • 1 篇 deep generative

机构

  • 2 篇 unist ulsan
  • 1 篇 keti seongnam
  • 1 篇 lg elect
  • 1 篇 modulabs

作者

  • 2 篇 baek seungryul
  • 2 篇 kim jihyeon
  • 2 篇 kim junsu
  • 1 篇 cho hoseong
  • 1 篇 tirunehl yihalem...
  • 1 篇 ku yunhoe
  • 1 篇 cha junuk

语言

  • 2 篇 英文
检索条件"主题词=Class Incremental Object Detection"
2 条 记 录,以下是1-10 订阅
排序:
SDDGR: Stable Diffusion-based Deep Generative Replay for class incremental object detection
SDDGR: Stable Diffusion-based Deep Generative Replay for Cla...
收藏 引用
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
作者: Kim, Junsu Kim, Jihyeon Cho, Hoseong Tirunehl, Yihalem Yimolal Baek, Seungryul UNIST Ulsan South Korea LG Elect Seoul South Korea KETI Seongnam South Korea
In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. Ho... 详细信息
来源: 评论
VLM-PL: Advanced Pseudo Labeling approach for class incremental object detection via Vision-Language Model
VLM-PL: Advanced Pseudo Labeling approach for Class Incremen...
收藏 引用
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
作者: Kim, Junsu Ku, Yunhoe Kim, Jihyeon Cha, Junuk Baek, Seungryul UNIST Ulsan South Korea MODULABS Seoul South Korea
In the field of class incremental object detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenar... 详细信息
来源: 评论