INTR_AI

https://github.com/dipanjyoti/INTR_AI

Science Score: 44.0%

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

✓
CITATION.cff file
Found 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 (3.8%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: dipanjyoti
License: mit
Language: Jupyter Notebook
Default Branch: main
Size: 2.33 MB

Statistics

Stars: 1
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created 8 months ago · Last pushed 6 months ago

Metadata Files

Readme License Citation

INTR-AI

Clone the repository

sh git clone https://github.com/dipanjyoti/UniPrompt-CAM.git cd UniPrompt-CAM

Environment Setup

Create python environment sh conda create -n uni_prompt python=3.7 conda activate uni_prompt source env_setup.sh

Download CUB INTR-UP Checkpoint

Download GBCU INTR-UP Checkpoint

Data Preparation

Follow the below format for data. datasets ├── dataset_name │ ├── train │ │ ├── class1 │ │ │ ├── img1.jpeg │ │ │ ├── img2.jpeg │ │ │ └── ... │ │ ├── class2 │ │ │ ├── img3.jpeg │ │ │ └── ... │ │ └── ... │ └── val │ ├── class1 │ │ ├── img4.jpeg │ │ ├── img5.jpeg │ │ └── ... │ ├── class2 │ │ ├── img6.jpeg │ │ └── ... │ └── ...

Evaluation and Interpretation

Follow Prompt-CAM GitHub link for mode details. sh CUDA_VISIBLE_DEVICES=0 python visualize.py --config ./experiment/config/prompt_cam/dino/cub/args.yaml --checkpoint ./checkpoints/dino/cub/model.pt --vis_cls 23

INTR Training

Follow Prompt-CAM GitHub link for mode details. sh CUDA_VISIBLE_DEVICES=0 python main.py --config ./experiment/config/prompt_cam/dino/cub/args.yaml

Owner

Login: dipanjyoti
Kind: user

Repositories: 1
Profile: https://github.com/dipanjyoti

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Prompt-CAM: Making Vision Transformers Interpretable for
  Fine-Grained Analysis
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Arpita
    family-names: Chowdhury
  - given-names: Dipanjyoti
    family-names: Paul
  - given-names: Zheda
    family-names: Mai
  - given-names: Jianyang
    family-names: Gu
  - given-names: Ziheng
    family-names: Zhang
  - given-names: Kazi Sajeed
    family-names: Mehrab
  - given-names: Elizabeth G.
    family-names: Campolongo
  - given-names: Daniel
    family-names: Rubenstein
  - given-names: Charles V.
    family-names: Stewart
  - given-names: Anuj
    family-names: Karpatne
  - given-names: Tanya
    family-names: Berger-Wolf
  - given-names: Yu
    family-names: Su
  - given-names: Wei-Lun
    family-names: Chao
identifiers:
  - type: url
    value: 'https://arxiv.org/pdf/2501.09333'
repository-code: 'https://github.com/Imageomics/Prompt_CAM'
abstract: >-
  We present a simple usage of pre-trained Vision
  Transformers (ViTs) for fine-grained analysis, aiming to
  identify and localize the traits that distinguish visually
  similar categories, such as different bird species or dog
  breeds. 
keywords:
  - explainable-ai
  - interpretable-ai
  - imageomics
  - fine-grained-classification
  - vision-transformer
  - interpretable
license: MIT
commit: Prompt-CAM
version: 1.0.0
date-released: '2025-03-24'

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science