# Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2207.03648 · HTML: https://mlsanity.com/paper/2207.03648/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 8 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [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)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [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)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/2103.13859/) (2021)
- [Gradients of Counterfactuals](https://mlsanity.com/paper/1611.02639/) (2016)
- [LFI-CAM: Learning Feature Importance for Better Visual Explanation](https://mlsanity.com/paper/2105.00937/) (2021)
- [Explaining image classifiers by removing input features using generative models](https://mlsanity.com/paper/1910.04256/) (2019)

## Built on by (most cited first, 20 of 20)

- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Knowledge Relation Rank Enhanced Heterogeneous Learning Interaction Modeling for Neural Graph Forgetting Knowledge Tracing](https://mlsanity.com/paper/2304.03945/) (2023)
- [Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models](https://mlsanity.com/paper/2305.03601/) (2023)
- [Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis](https://mlsanity.com/paper/2504.12151/) (2025)
- [Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposal](https://mlsanity.com/paper/2302.03180/) (2023)
- [DKT-STDRL: Spatial and Temporal Representation Learning Enhanced Deep Knowledge Tracing for Learning Performance Prediction](https://mlsanity.com/paper/2302.11569/) (2023)
- [COMIX: Compositional Explanations using Prototypes](https://mlsanity.com/paper/2501.06059/) (2025)
- [Image Compressed Sensing with Multi-scale Dilated Convolutional Neural Network](https://mlsanity.com/paper/2209.13761/) (2022)
- [JSRNN: Joint Sampling and Reconstruction Neural Networks for High Quality Image Compressed Sensing](https://mlsanity.com/paper/2211.05963/) (2022)
- [Photovoltaic Panel Defect Detection Based on Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5](https://mlsanity.com/paper/2303.00886/) (2023)
- [Graph Neural Networks Enhanced Smart Contract Vulnerability Detection of Educational Blockchain](https://mlsanity.com/paper/2303.04477/) (2023)
- [Learning Behavior Recognition in Smart Classroom with Multiple Students Based on YOLOv5](https://mlsanity.com/paper/2303.10916/) (2023)
- [Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers](https://mlsanity.com/paper/2310.12553/) (2023)
- [Multi-Scale Deformable Transformers for Student Learning Behavior Detection in Smart Classroom](https://mlsanity.com/paper/2410.07834/) (2024)
- [A Closed-Loop Personalized Learning Agent Integrating Neural Cognitive Diagnosis, Bounded-Ability Adaptive Testing, and LLM-Driven Feedback](https://mlsanity.com/paper/2510.22559/) (2025)
- [TLCD: A Deep Transfer Learning Framework for Cross-Disciplinary Cognitive Diagnosis](https://mlsanity.com/paper/2510.23062/) (2025)
- [Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training](https://mlsanity.com/paper/2510.25042/) (2025)
- [Mask-Robust Face Verification for Online Learning via YOLOv5 and Residual Networks](https://mlsanity.com/paper/2510.25184/) (2025)
- [Deep learning recognition and analysis of Volatile Organic Compounds based on experimental and synthetic infrared absorption spectra](https://mlsanity.com/paper/2512.06059/) (2025)
- [Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations](https://mlsanity.com/paper/2608.12299/) (2026)

## Abstract (arXiv)

The black-box nature of Deep Neural Networks (DNNs) severely hinders its performance improvement and application in specific scenes. In recent years, class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. However, when this method uses backpropagation to obtain gradients, it will cause noise in the saliency map, and even locate features that are irrelevant to decisions. In this paper, we propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimizes the gradients derived from the backpropagation and turns all of them into positive gradients to enhance the visual features of output neurons' activation, and improve the localization ability of the saliency map. The framework of Abs-CAM is divided into two phases: generating initial saliency map and generating final saliency map. The first phase improves the localization ability of the saliency map by optimizing the gradient, and the second phase linearly combines the initial saliency map with the original image to enhance the semantic information of the saliency map. We conduct qualitative and quantitative evaluation of the proposed method, including Deletion, Insertion, and Pointing Game. The experimental results show that the Abs-CAM can obviously eliminate the noise in the saliency map, and can better locate the features related to decisions, and is superior to the previous methods in recognition and localization tasks.