# TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

arXiv: https://arxiv.org/abs/2110.05182 · HTML: https://mlsanity.com/paper/2110.05182/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 30 of 34)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention](https://mlsanity.com/paper/1703.10631/) (2017)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [MDNet: A Semantically and Visually Interpretable Medical Image Diagnosis Network](https://mlsanity.com/paper/1707.02485/) (2017)
- [Interpreting CNN Knowledge via an Explanatory Graph](https://mlsanity.com/paper/1708.01785/) (2017)
- [Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1908.02686/) (2019)
- [Re-Identification with Consistent Attentive Siamese Networks](https://mlsanity.com/paper/1811.07487/) (2018)
- [Coarse-to-fine Semantic Segmentation from Image-level Labels](https://mlsanity.com/paper/1812.10885/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Mask-Based Adversarial Defense Scheme](https://mlsanity.com/paper/2204.11837/) (2022)
- [Super-resolution Reconstruction of Single Image for Latent features](https://mlsanity.com/paper/2211.12845/) (2022)

## Abstract (arXiv)

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural networks. Compared to iteration based saliency methods, single backward pass based saliency methods benefit from faster speed, and they are widely used in downstream visual tasks. Thus, we focus on single backward pass based methods. However, existing methods in this category struggle to uccessfully produce fine-grained saliency maps concentrating on specific target classes. That said, producing faithful saliency maps satisfying both target-selectiveness and fine-grainedness using a single backward pass is a challenging problem in the field. To mitigate this problem, we revisit the gradient flow inside the network, and find that the entangled semantics and original weights may disturb the propagation of target-relevant saliency. Inspired by those observations, we propose a novel visual saliency method, termed Target-Selective Gradient Backprop (TSGB), which leverages rectification operations to effectively emphasize target classes and further efficiently propagate the saliency to the image space, thereby generating target-selective and fine-grained saliency maps. The proposed TSGB consists of two components, namely, TSGB-Conv and TSGB-FC, which rectify the gradients for convolutional layers and fully-connected layers, respectively. Extensive qualitative and quantitative experiments on the ImageNet and Pascal VOC datasets show that the proposed method achieves more accurate and reliable results than the other competitive methods. Code is available at https://github.com/123fxdx/CNNvisualizationTSGB.