Saliency - Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

Overview

Saliency Methods

🔴    Now framework-agnostic! (Example core notebook)   🔴

🔗    For further explanation of the methods and more examples of the resulting maps, see our Github Pages website   🔗

If upgrading from an older version, update old imports to import saliency.tf1 as saliency. We provide wrappers to make the framework-agnostic version compatible with TF1 models. (Example TF1 notebook)

Introduction

This repository contains code for the following saliency techniques:

*Developed by PAIR.

This list is by no means comprehensive. We are accepting pull requests to add new methods!

Download

# To install the core subpackage:
pip install saliency

# To install core and tf1 subpackages:
pip install saliency[tf1]

or for the development version:

git clone https://github.com/pair-code/saliency
cd saliency

Usage

The saliency library has two subpackages:

  • core uses a generic call_model_function which can be used with any ML framework.
  • tf1 accepts input/output tensors directly, and sets up the necessary graph operations for each method.

Core

Each saliency mask class extends from the CoreSaliency base class. This class contains the following methods:

  • GetMask(x_value, call_model_function, call_model_args=None): Returns a mask of the shape of non-batched x_value given by the saliency technique.
  • GetSmoothedMask(x_value, call_model_function, call_model_args=None, stdev_spread=.15, nsamples=25, magnitude=True): Returns a mask smoothed of the shape of non-batched x_value with the SmoothGrad technique.

The visualization module contains two methods for saliency visualization:

  • VisualizeImageGrayscale(image_3d, percentile): Marginalizes across the absolute value of each channel to create a 2D single channel image, and clips the image at the given percentile of the distribution. This method returns a 2D tensor normalized between 0 to 1.
  • VisualizeImageDiverging(image_3d, percentile): Marginalizes across the value of each channel to create a 2D single channel image, and clips the image at the given percentile of the distribution. This method returns a 2D tensor normalized between -1 to 1 where zero remains unchanged.

If the sign of the value given by the saliency mask is not important, then use VisualizeImageGrayscale, otherwise use VisualizeImageDiverging. See the SmoothGrad paper for more details on which visualization method to use.

call_model_function

call_model_function is how we pass inputs to a given model and receive the outputs necessary to compute saliency masks. The description of this method and expected output format is in the CoreSaliency description, as well as separately for each method.

Examples

This example iPython notebook showing these techniques is a good starting place.

Here is a condensed example of using IG+SmoothGrad with TensorFlow 2:

import saliency.core as saliency
import tensorflow as tf

...

# call_model_function construction here.
def call_model_function(x_value_batched, call_model_args, expected_keys):
	tape = tf.GradientTape()
	grads = np.array(tape.gradient(output_layer, images))
	return {saliency.INPUT_OUTPUT_GRADIENTS: grads}

...

# Load data.
image = GetImagePNG(...)

# Compute IG+SmoothGrad.
ig_saliency = saliency.IntegratedGradients()
smoothgrad_ig = ig_saliency.GetSmoothedMask(image, 
											call_model_function, 
                                            call_model_args=None)

# Compute a 2D tensor for visualization.
grayscale_visualization = saliency.VisualizeImageGrayscale(
    smoothgrad_ig)

TF1

Each saliency mask class extends from the TF1Saliency base class. This class contains the following methods:

  • __init__(graph, session, y, x): Constructor of the SaliencyMask. This can modify the graph, or sometimes create a new graph. Often this will add nodes to the graph, so this shouldn't be called continuously. y is the output tensor to compute saliency masks with respect to, x is the input tensor with the outer most dimension being batch size.
  • GetMask(x_value, feed_dict): Returns a mask of the shape of non-batched x_value given by the saliency technique.
  • GetSmoothedMask(x_value, feed_dict): Returns a mask smoothed of the shape of non-batched x_value with the SmoothGrad technique.

The visualization module contains two visualization methods:

  • VisualizeImageGrayscale(image_3d, percentile): Marginalizes across the absolute value of each channel to create a 2D single channel image, and clips the image at the given percentile of the distribution. This method returns a 2D tensor normalized between 0 to 1.
  • VisualizeImageDiverging(image_3d, percentile): Marginalizes across the value of each channel to create a 2D single channel image, and clips the image at the given percentile of the distribution. This method returns a 2D tensor normalized between -1 to 1 where zero remains unchanged.

If the sign of the value given by the saliency mask is not important, then use VisualizeImageGrayscale, otherwise use VisualizeImageDiverging. See the SmoothGrad paper for more details on which visualization method to use.

Examples

This example iPython notebook shows these techniques is a good starting place.

Another example of using GuidedBackprop with SmoothGrad from TensorFlow:

from saliency.tf1 import GuidedBackprop
from saliency.tf1 import VisualizeImageGrayscale
import tensorflow.compat.v1 as tf

...
# Tensorflow graph construction here.
y = logits[5]
x = tf.placeholder(...)
...

# Compute guided backprop.
# NOTE: This creates another graph that gets cached, try to avoid creating many
# of these.
guided_backprop_saliency = GuidedBackprop(graph, session, y, x)

...
# Load data.
image = GetImagePNG(...)
...

smoothgrad_guided_backprop =
    guided_backprop_saliency.GetMask(image, feed_dict={...})

# Compute a 2D tensor for visualization.
grayscale_visualization = visualization.VisualizeImageGrayscale(
    smoothgrad_guided_backprop)

Conclusion/Disclaimer

If you have any questions or suggestions for improvements to this library, please contact the owners of the PAIR-code/saliency repository.

This is not an official Google product.

Owner
PAIR code
Code repositories for projects from the People+AI Research (PAIR) Initiative
PAIR code
NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall

OptiPrompt This is the PyTorch implementation of the paper Factual Probing Is [MASK]: Learning vs. Learning to Recall. We propose OptiPrompt, a simple

Princeton Natural Language Processing 150 Dec 20, 2022
Automatic Image Background Subtraction

Automatic Image Background Subtraction This repo contains set of scripts for automatic one-shot image background subtraction task using the following

Oleg Sémery 6 Dec 05, 2022
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

DeepCTR DeepCTR is a Easy-to-use,Modular and Extendible package of deep-learning based CTR models along with lots of core components layers which can

浅梦 6.6k Jan 08, 2023
Blind Video Temporal Consistency via Deep Video Prior

deep-video-prior (DVP) Code for NeurIPS 2020 paper: Blind Video Temporal Consistency via Deep Video Prior PyTorch implementation | paper | project web

Chenyang LEI 272 Dec 21, 2022
C3d-pytorch - Pytorch porting of C3D network, with Sports1M weights

C3D for pytorch This is a pytorch porting of the network presented in the paper Learning Spatiotemporal Features with 3D Convolutional Networks How to

Davide Abati 311 Jan 06, 2023
Open-source code for Generic Grouping Network (GGN, CVPR 2022)

Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity Pytorch implementation for "Open-World Instance Segmen

Meta Research 99 Dec 06, 2022
gtfs2vec - Learning GTFS Embeddings for comparing PublicTransport Offer in Microregions

gtfs2vec This is a companion repository for a gtfs2vec - Learning GTFS Embeddings for comparing PublicTransport Offer in Microregions publication. Vis

Politechnika Wrocławska - repozytorium dla informatyków 5 Oct 10, 2022
🏖 Keras Implementation of Painting outside the box

Keras implementation of Image OutPainting This is an implementation of Painting Outside the Box: Image Outpainting paper from Standford University. So

Bendang 1.1k Dec 10, 2022
Implementing DeepMind's Fast Reinforcement Learning paper

Fast Reinforcement Learning This is a repo where I implement the algorithms in the paper, Fast reinforcement learning with generalized policy updates.

Marcus Chiam 6 Nov 28, 2022
Realistic lighting in ursina!

Ursina Lighting Realistic lighting in ursina! If you want to have realistic lighting in ursina, import the UrsinaLighting.py in your project and use t

17 Jul 07, 2022
Using PyTorch Perform intent classification using three different models to see which one is better for this task

Using PyTorch Perform intent classification using three different models to see which one is better for this task

Yoel Graumann 1 Feb 14, 2022
Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

L2F - Learning to Forget for Meta-Learning Sungyong Baik, Seokil Hong, Kyoung Mu Lee Source code for CVPR 2020 paper "Learning to Forget for Meta-Lear

Sungyong Baik 29 May 22, 2022
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

EfficientZero (NeurIPS 2021) Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021. Environments Effi

Weirui Ye 671 Jan 03, 2023
StyleGAN of All Trades: Image Manipulation withOnly Pretrained StyleGAN

StyleGAN of All Trades: Image Manipulation withOnly Pretrained StyleGAN This is the PyTorch implementation of StyleGAN of All Trades: Image Manipulati

360 Dec 28, 2022
3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans.

3DMV 3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans. This work is based on our ECCV'18 p

Владислав Молодцов 0 Feb 06, 2022
This is the repo for our work "Towards Persona-Based Empathetic Conversational Models" (EMNLP 2020)

Towards Persona-Based Empathetic Conversational Models (PEC) This is the repo for our work "Towards Persona-Based Empathetic Conversational Models" (E

Zhong Peixiang 35 Nov 17, 2022
Learning Features with Parameter-Free Layers (ICLR 2022)

Learning Features with Parameter-Free Layers (ICLR 2022) Dongyoon Han, YoungJoon Yoo, Beomyoung Kim, Byeongho Heo | Paper NAVER AI Lab, NAVER CLOVA Up

NAVER AI 65 Dec 07, 2022
Bravia core script for python

Bravia-Core-Script You need to have a mandatory account If this L3 does not work, try another L3. enjoy

5 Dec 26, 2021
img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation Figure 1: We estimate the 6DoF rigid transformation of a 3D face (rendered in si

Vítor Albiero 519 Dec 29, 2022
Official implementation of FCL-taco2: Fast, Controllable and Lightweight version of Tacotron2 @ ICASSP 2021

FCL-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech synthesis (ICASSP 2021) Paper | Demo Block diagram of FCL-taco2, where the decode

Disong Wang 39 Sep 28, 2022