Imageomics/Prompt_CAM
This is an official implementation for PROMPT-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis (CVPR'25). Explore fine-grained trait distinctions between different specified species.
This project helps scientists and researchers understand why an AI model identifies specific traits in images, especially for fine-grained distinctions between similar species like different bird types. You provide images of various species, and it outputs visual heatmaps highlighting the exact features the AI used to classify them. This is for biologists, conservationists, or anyone analyzing subtle visual differences in biological or other fine-grained image datasets.
Use this if you need to visualize and interpret what an AI model considers important when distinguishing between very similar categories in images, for example, identifying specific features of different bird species or dog breeds.
Not ideal if you are looking for a general image classifier that simply tells you what an image contains without needing to understand its reasoning.
Stars
71
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Imageomics/Prompt_CAM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with...
roflcoopter/viseron
Self-hosted, local only NVR and AI Computer Vision software. With features such as object...
blakeblackshear/frigate
NVR with realtime local object detection for IP cameras
levan92/deep_sort_realtime
A really more real-time adaptation of deep sort
notAI-tech/NudeNet
Lightweight nudity detection