paper-with-me

Papers

Sanity Checks for Saliency Methods Explaining Object Detectors

2023-06-04 · Deepan Chakravarthi Padmanabhan, Paul G. Plöger, Octavio Arriaga, Matias Valdenegro-Toro

Saliency methods are frequently used to explain Deep Neural Network-based models. Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests. However, on extending the tests for various state of the art object detectors we illustrate that the ability to explain a model is more dependent on the model itself than the explanation method. We perform sanity checks for object detection and define new qualitative criteria to evaluate the saliency explanations, both for object classification and bounding box decisions, using Guided Backpropagation, Integrated Gradients, and their Smoothgrad versions, together with Faster R-CNN, SSD, and EfficientDet-D0, trained on COCO. In addition, the sensitivity of the explanation method to model parameters and data labels varies class-wise motivating to perform the sanity checks for each class. We find that EfficientDet-D0 is the most interpretable method independent of the saliency method, which passes the sanity checks with little problems.

📄 PDF Abstract BibTeX arXiv:2306.02424

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

fail 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
SSD SSD is a single-stage object detection method that discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per…
RoIPool 설명 없음
RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Similar Papers 제목 키워드 기반

Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents

2021-01-18 · Tobias Huber, Benedikt Limmer, Elisabeth André

One of the most prominent methods for explaining the behavior of Deep Reinforcement Learning (DRL) agents is the generation of saliency maps that show how much each pixel attributed to the agents' decision. However, ther…

Atari GamesBenchmarkingDeep Reinforcement LearningFeature Importance+1

Investigating sanity checks for saliency maps with image and text classification

2021-06-08 · Narine Kokhlikyan, Vivek Miglani, Bilal Alsallakh, Miguel Martin 외

Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text modality and show that the conclusions made…

text-classificationText Classification

Revisiting Sanity Checks for Saliency Maps

2021-10-27 · Gal Yona, Daniel Greenfeld

Saliency methods are a popular approach for model debugging and explainability. However, in the absence of ground-truth data for what the correct maps should be, evaluating and comparing different approaches remains a lo…

A Simple Technique to Enable Saliency Methods to Pass the Sanity Checks

2019-09-25 · Arushi Gupta, Sanjeev Arora

{\em Saliency methods} attempt to explain a deep net's decision by assigning a {\em score} to each feature/pixel in the input, often doing this credit-assignment via the gradient of the output with respect to input. Re…

Sanity checks for patch visualisation in prototype-based image classification

2023-10-25 · Romain Xu-Darme, Georges Quénot, Zakaria Chihani, Marie-Christine Rousset

In this work, we perform an analysis of the visualisation methods implemented in ProtoPNet and ProtoTree, two self-explaining visual classifiers based on prototypes. We show that such methods do not correctly identify th…

image-classificationImage Classification