Ross ROSS = Recommend OSS · open-source software intelligence for agents

AIFengheshu/Plug-play-modules resource

2025年全网最全即插即用模块，免费分享！CVPR2025，AAAI2025，ICLR2025，TNNLS2025，arXiv2025......包含人工智能全领域（机器学习、深度学习等），适用于图像分类、目标检测、实例分割、语义分割、全景分割、姿态识别、医学图像分割、视频目标分割、图像抠图、图像编辑、单目标跟踪、多目标跟踪、行人重识别、RGBT、图像去噪、去雨、去雾、去阴影、去模糊、超分辨率、去反光、去摩尔纹、图像恢复、图像修复、高光谱图像恢复、图像融合、图像上色、高动态范围成像、视频与图像压缩、3D点云、3D目标检测、3D语义分割、3D姿态识别等各类计算机视觉和图像处理任务，以及自然语言处理、大语言模型、多模态等其他各类人工智能相关任务。持续更新中...... observed · 2026-08-28

github.com/AIFengheshu/Plug-play-modules · Python observed · 2026-08-28

Health v2 · maintenance only

32/100

  • Activity 23
  • Release rhythm 35
  • Longevity 49

Flags: no_releases no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 693
  • days_rel: n/a
  • days_push: 467
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1606 stars · 122 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated collection of plug-and-play neural network modules (attention mechanisms, convolutions, fusion blocks) extracted from 2024-2025 papers like CVPR, AAAI, ECCV, and ICLR. Each module is provided as a standalone Python file with paper links and Chinese-language explanations, targeting computer vision and broader AI tasks.

Use cases

  • find plug-and-play attention modules for my model
  • boost image segmentation accuracy with drop-in modules
  • implement wavelet convolution from ECCV 2024
  • find reusable blocks for object detection backbones
  • learn how recent paper modules work with code
  • add feature fusion modules to my CNN
  • find modules for image restoration and super-resolution

When to choose

  • you want ready-to-copy PyTorch modules from recent papers to insert into your own architecture
  • you are doing computer vision research and want to experiment with attention or fusion blocks
  • you want paper links plus code in one place

When to avoid

  • you need a maintained, tested library with stable APIs and CI
  • you need production-grade code with a license for commercial use (no license is provided)
  • you need full model implementations rather than isolated modules

Facets

learning-resource · maturity active

machine-learning deep-learning image-processing computer-vision nlp computer-vision image-processing deep-learning machine-learning tutorials python plug-and-play-modules attention-mechanisms paper-implementations awesome-list research-code pytorch natural-language-processing

1 source

Member repositories

RepositoryRoleHealth v2
AIFengheshu/Plug-play-modulesmain32

For agents

markdown · JSON · MCP: product_card(name="AIFengheshu/Plug-play-modules")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem