Explainability for Vision Transformers (in PyTorch)

Overview

Explainability for Vision Transformers (in PyTorch)

This repository implements methods for explainability in Vision Transformers.

See also https://jacobgil.github.io/deeplearning/vision-transformer-explainability

Currently implemented:

  • Attention Rollout.

  • Gradient Attention Rollout for class specific explainability. This is our attempt to further build upon and improve Attention Rollout.

  • TBD Attention flow is work in progress.

Includes some tweaks and tricks to get it working:

  • Different Attention Head fusion methods,
  • Removing the lowest attentions.

Usage

  • From code
from vit_grad_rollout import VITAttentionGradRollout

model = torch.hub.load('facebookresearch/deit:main', 
'deit_tiny_patch16_224', pretrained=True)
grad_rollout = VITAttentionGradRollout(model, discard_ratio=0.9, head_fusion='max')
mask = grad_rollout(input_tensor, category_index=243)
  • From the command line:
python vit_explain.py --image_path  --head_fusion  --discard_ratio  --category_index 

If category_index isn't specified, Attention Rollout will be used, otherwise Gradient Attention Rollout will be used.

Notice that by default, this uses the 'Tiny' model from Training data-efficient image transformers & distillation through attention hosted on torch hub.

Where did the Transformer pay attention to in this image?

Image Vanilla Attention Rollout With discard_ratio+max fusion

Gradient Attention Rollout for class specific explainability

The Attention that flows in the transformer passes along information belonging to different classes. Gradient roll out lets us see what locations the network paid attention too, but it tells us nothing about if it ended up using those locations for the final classification.

We can multiply the attention with the gradient of the target class output, and take the average among the attention heads (while masking out negative attentions) to keep only attention that contributes to the target category (or categories).

Where does the Transformer see a Dog (category 243), and a Cat (category 282)?

Where does the Transformer see a Musket dog (category 161) and a Parrot (category 87):

Tricks and Tweaks to get this working

Filtering the lowest attentions in every layer

--discard_ratio

Removes noise by keeping the strongest attentions.

Results for dIfferent values:

Different Attention Head Fusions

The Attention Rollout method suggests taking the average attention accross the attention heads,

but emperically it looks like taking the Minimum value, Or the Maximum value combined with --discard_ratio, works better.

--head_fusion

Image Mean Fusion Min Fusion

References

Requirements

pip install timm

Owner
Jacob Gildenblat
Machine learning / Computer Vision developer.
Jacob Gildenblat
Segmentation Training Pipeline

Segmentation Training Pipeline This package is a part of Musket ML framework. Reasons to use Segmentation Pipeline Segmentation Pipeline was developed

Musket ML 52 Dec 12, 2022
JDet is Object Detection Framework based on Jittor.

JDet is Object Detection Framework based on Jittor.

135 Dec 14, 2022
This package is for running the semantic SLAM algorithm using extracted planar surfaces from the received detection

Semantic SLAM This package can perform optimization of pose estimated from VO/VIO methods which tend to drift over time. It uses planar surfaces extra

Hriday Bavle 125 Dec 02, 2022
Apply our monocular depth boosting to your own network!

MergeNet - Boost Your Own Depth Boost custom or edited monocular depth maps using MergeNet Input Original result After manual editing of base You can

Computational Photography Lab @ SFU 142 Dec 17, 2022
This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields Project Page | Paper | Supplementary | Video | Slides | Blog | Talk If

1.1k Dec 30, 2022
Two-stage CenterNet

Probabilistic two-stage detection Two-stage object detectors that use class-agnostic one-stage detectors as the proposal network. Probabilistic two-st

Xingyi Zhou 1.1k Jan 03, 2023
Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Status: Archive (code is provided as-is, no updates expected) InfoGAN Code for reproducing key results in the paper InfoGAN: Interpretable Representat

OpenAI 1k Dec 19, 2022
Simple Baselines for Human Pose Estimation and Tracking

Simple Baselines for Human Pose Estimation and Tracking News Our new work High-Resolution Representations for Labeling Pixels and Regions is available

Microsoft 2.7k Jan 05, 2023
Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning Reference Abeßer, J. & Müller, M. Towards Audio Domain Adapt

Jakob Abeßer 2 Jul 06, 2022
Matlab Python Heuristic Battery Opt - SMOP conversion and manual conversion

SMOP is Small Matlab and Octave to Python compiler. SMOP translates matlab to py

Tom Xu 1 Jan 12, 2022
ChebLieNet, a spectral graph neural network turned equivariant by Riemannian geometry on Lie groups.

ChebLieNet: Invariant spectral graph NNs turned equivariant by Riemannian geometry on Lie groups Hugo Aguettaz, Erik J. Bekkers, Michaël Defferrard We

haguettaz 12 Dec 10, 2022
This is a Deep Leaning API for classifying emotions from human face and human audios.

Emotion AI This is a Deep Leaning API for classifying emotions from human face and human audios. Starting the server To start the server first you nee

crispengari 5 Oct 02, 2022
This repo provides code for QB-Norm (Cross Modal Retrieval with Querybank Normalisation)

This repo provides code for QB-Norm (Cross Modal Retrieval with Querybank Normalisation) Usage example python dynamic_inverted_softmax.py --sims_train

36 Dec 29, 2022
Pytorch implementation of the paper Time-series Generative Adversarial Networks

TimeGAN-pytorch Pytorch implementation of the paper Time-series Generative Adversarial Networks presented at NeurIPS'19. Jinsung Yoon, Daniel Jarrett

Zhiwei ZHANG 21 Nov 24, 2022
A small library of 3D related utilities used in my research.

utils3D A small library of 3D related utilities used in my research. Installation Install via GitHub pip install git+https://github.com/Steve-Tod/util

Zhenyu Jiang 8 May 20, 2022
toroidal - a lightweight transformer library for PyTorch

toroidal - a lightweight transformer library for PyTorch Toroidal transformers are of smaller size and lower weight than the more common E-I types. Th

MathInf GmbH 64 Jan 07, 2023
OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework Introduction OpenFed is a foundational library for federated learning

25 Dec 12, 2022
Includes PyTorch -> Keras model porting code for ConvNeXt family of models with fine-tuning and inference notebooks.

ConvNeXt-TF This repository provides TensorFlow / Keras implementations of different ConvNeXt [1] variants. It also provides the TensorFlow / Keras mo

Sayak Paul 87 Dec 06, 2022
This is an open solution to the Home Credit Default Risk challenge 🏡

Home Credit Default Risk: Open Solution This is an open solution to the Home Credit Default Risk challenge 🏡 . More competitions 🎇 Check collection

minerva.ml 427 Dec 27, 2022
Details about the wide minima density hypothesis and metrics to compute width of a minima

wide-minima-density-hypothesis Details about the wide minima density hypothesis and metrics to compute width of a minima This repo presents the wide m

Nikhil Iyer 9 Dec 27, 2022