Data

Tools

Indexes

Applications

Experiments

Open Source Science

model-guidance

Code for the paper: Studying How to Efficiently and Effectively Guide Models with Explanations. ICCV 2023.

https://github.com/sukrutrao/model-guidance

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 (10.5%) to scientific vocabulary

Keywords

computer-vision deep-learning explainability iccv2023 model-guidance python
Last synced: 6 months ago · JSON representation ·

Repository

Code for the paper: Studying How to Efficiently and Effectively Guide Models with Explanations. ICCV 2023.

Basic Info
Statistics
  • Stars: 19
  • Watchers: 2
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Topics
computer-vision deep-learning explainability iccv2023 model-guidance python
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

Studying How to Efficiently and Effectively Guide Models with Explanations

Sukrut Rao* · Moritz Böhle* · Amin Parchami-Araghi · Bernt Schiele

IEEE/CVF International Conference on Computer Vision (ICCV) 2023

Paper | Code | Video

Setup

Prerequisites

All the required packages can be installed using conda with the provided environment.yml file.

Data

Scripts to download and preprocess the VOC2007 and COCO2014 datasets have been provided in the datasets directory. Please refer to the README file provided there.

ImageNet Pre-trained Weights

A script to download the pre-trained ImageNet weights for B-cos and X-DNN backbones has been provided in the weights directory. Please refer to the README file provided there.

Training Models

To train a model, use:

bash python train.py [options]

The list of options and their descriptions can be found by using:

bash python train.py -h

Training without Model Guidance

For example, to train a B-cos model on VOC2007, use:

bash python train.py --model_backbone bcos --dataset VOC2007 --learning_rate 1e-4 --train_batch_size 64 --total_epochs 300

Fine-tuning with Model Guidance

For example, to optimize B-cos attributions using the Energy loss at the Input layer, use:

```bash python train.py --modelbackbone bcos --dataset VOC2007 --learningrate 1e-4 --trainbatchsize 64 --totalepochs 50 --optimizeexplanations --modelpath models/VOC2007/bcosstandardattrNoneloclossNoneorigNoneresnet50lr1e-04sll1.0layerInput/modelcheckpointf1best.pt --localizationlosslambda 1e-3 --layer Input --localizationlossfn Energy --pareto

```

Code for training on the Waterbirds-100 dataset and scripts for visualizing explanations will be added soon.

Acknowledgements

This repository uses and builds upon code from the following repositories: * B-cos/B-cos-v2 * stevenstalder/NN-Explainer * visinf/fast-axiomatic-attribution

Citation

Please cite our paper as follows:

tex @InProceedings{Rao_2023_ICCV, author = {Rao, Sukrut and B\"ohle, Moritz and Parchami-Araghi, Amin and Schiele, Bernt}, title = {Studying How to Efficiently and Effectively Guide Models with Explanations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1922-1933} }

Owner

  • Name: Sukrut Rao
  • Login: sukrutrao
  • Kind: user
  • Location: Germany
  • Company: Max Planck Institute for Informatics

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "Please cite the paper as below."
preferred-citation:
  authors:
    - family-names: Rao
      given-names: Sukrut
      orcid: "https://orcid.org/0000-0001-8896-7619"
    - family-names: Böhle
      given-names: Moritz
    - family-names: Parchami-Araghi
      given-names: Amin
    - family-names: Schiele
      given-names: Bernt
      orcid: "https://orcid.org/0000-0001-9683-5237"
  title: "Studying How to Efficiently and Effectively Guide Models with Explanations"
  type: conference-paper
  collection-title: "IEEE/CVF International Conference on Computer Vision (ICCV)"
  year: 2023

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1