Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''
| Date | Stars |
|---|---|
| 2026-07-31 | 1372 |
| 2026-08-02 | 1373 |
| 2026-08-06 | 1373 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# CVinW Readings [](https://github.com/Computer-Vision-in-the-Wild/CVinW_Readings) ``[Computer Vision in the Wild (CVinW)](https://computer-vision-in-the-wild.github.io/eccv-2022/)'' is an emerging research field. This writeup provides a quick introduction of CVinW and maintains a collection of papers on the topic. If you find some missing papers or resources, please open issues or pull requests (recommended). # Table of Contents - [What is Computer Vision in the Wild (CVinW)?](#what-is-computer-vision-in-the-wild) - [Goals of CVinW](#star-goals-of-cvinw) - [Task Transfer Scenarios are Broad](#one-task-transfer-scenarios-are-broad) - [Task Transfer Cost is Low](#two-task-transfer-cost-is-low ) - [Benchmarks](#cinema-benchmarks) - [News](#loudspeaker-news) - [Papers on Task-level Transfer with Pre-trained Models](#fire-papers-on-task-level-transfer-with-pre-trained-models) - [Image Classification in the Wild](#orange_book-image-classification-in-the-wild) - [Object Detection in the Wild](#orange_book-object-detection-in-the-wild) - [Segmentation in the Wild](#orange_book-segmentation-in-the-wild) - [Video Classification in the Wild](#orange_book-video-classification-in-the-wild) - [Grounded Image Generation in the Wild](#orange_book-grounded-image-generation-in-the-wild) - [Large Multimodal Models](#orange_book-large-multimodal-models) - [Others](#orange_book-other-visual-recognition-in-the-wild) - [Papers on Efficient Model Adaptation](#snowflake-papers-on-efficient-model-adaptation) - [Parameter-Efficient Methods](#blue_book-parameter-efficient-methods) - [Others](#blue_book-other-efficient-model-adaptation-methods) - [Papers on Out-of-domain Generalization](#eye-papers-on-out-of-domain-generalization) - [Surveys](#green_book-surveys) - [Out-of-domain Generalization](#green_book-out-of-domain-generalization) - [Robust Models](#green_book-robust-models) - [Acknowledgements](#beers-acknowledgements) # What is Computer Vision in the Wild? ### :star: Goals of CVinW Developing a transferable foundation model/system that can *effortlessly* adapt to *a large range of visual tasks* in the wild. It comes with two key factors: (i) The task transfer scenarios are broad, and (ii) The task transfer cost is low. The main idea is illustrated as follows, please see the detailed description in [ELEVATER paper](https://arxiv.org/abs/2204.08790). ### :one: Task Transfer Scenarios are Broad We illustrate and compare CVinW with other settings using a 2D chart in Figure 1, where the space is constructed with two orthogonal dimensions: input image distribution and output concept set. The 2D chart is divided into four quadrants, based on how the model evaluation stage is different from model development stage. For any visual recognition problems at different granularity such as image classification, object detection and segmentation, the modeling setup cann be categorized into one of the four settings. We see an emerging trend on moving towards CVinW. Interested in the various pre-trained vision models that move towards CVinW? please check out Section :fire:[``Papers on Task-level Transfer with Pre-trained Models''](#fire-papers-on-task-level-transfer-with-pre-trained-models). <table> <tr> <td width="50%"> <ul> <li><b>The Close-Set Setting. </b> Both training and evaluation distributions are consistent in both dimensions, a typical setting in ML/CV textbooks.</li> <li><b>Open-Set/Vocabulary/World Setting.</b> It allows new concepts in evaluation, while typically remains the same visual domain. Please see examples in <a href='https://arxiv.org/abs/1707.00600'>image classification</a> and <a href='https://arxiv.org/abs/2011.10678'>object detection</a>. </li> <li><b>Domain Generalization Setting.</b> Domain shift allows new visual domain in evaluation, while typically remains the same
Excerpt of 70,198 characters
Read on GitHub
48
Brian Li · Advanced Machine Intelligence
12
6
5
Yuanhan Zhang · Nanyang Technological University · Singapore
3
2
Ikko Eltociear Ashimine · Japan
1
1
Shilong Liu · Princeton University
1
1
1
Haotian Liu · xAI · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7b08b32a2da8db86, desc:computer vision