mmdetection-c2former

可见光/红外光双模态目标检测: C2Former在MMDetection(Cascade-RCNN)上的实现

https://github.com/ex-imanity/mmdetection-c2former

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

可见光/红外光双模态目标检测: C2Former在MMDetection(Cascade-RCNN)上的实现

Basic Info
  • Host: GitHub
  • Owner: Ex-imanity
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 15 MB
Statistics
  • Stars: 9
  • Watchers: 1
  • Forks: 0
  • Open Issues: 3
  • Releases: 0
Created about 1 year ago · Last pushed 12 months ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

C2Former on MMdetection

C2FormerMMDetectionCascade R-CNNM3FD

Results

results

results

BDLfusion

results

results

BDLfusionLiuZhu-CV/BDLFusion: Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond (IJCAI 23)

Checkpoints

dgpp

Installation

MMdetection2.28.2MMrotatemmdet2.28

Dataset

M3FD

JinyuanLiu-CV/TarDAL: CVPR 2022 | Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection.

VOCM3FD

Getting Started

Train with a single GPU.

shell python tools/train.py configs/cascade_rcnn/cascade_rcnn_c2former_fpn_1x_m3fd.py --work-dir work_dirs/cascade_rcnn_c2former_fpn_1x_m3fd

Notes

evaluation metricsPascal VOC/JPEGImages"*.png""*tir.png"M3FD/Annotations/ImageSets/MainVOC

mmdetdetectorMMDetection

Owner

  • Name: Undecimber
  • Login: Ex-imanity
  • Kind: user

GitHub Events

Total
  • Issues event: 3
  • Watch event: 12
  • Issue comment event: 10
  • Push event: 4
  • Create event: 1
Last Year
  • Issues event: 3
  • Watch event: 12
  • Issue comment event: 10
  • Push event: 4
  • Create event: 1