TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Deep Inside Convolutional Networks: Visualising Image Clas...

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Karen Simonyan, Andrea Vedaldi, Andrew Zisserman

2013-12-20Weakly-Supervised Object SegmentationInterpretability Techniques for Deep LearningImage ClassificationSemantic SegmentationGeneral ClassificationImage Attribution
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCode

Abstract

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [Erhan et al., 2009], thus visualising the notion of the class, captured by a ConvNet. The second technique computes a class saliency map, specific to a given image and class. We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets. Finally, we establish the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks [Zeiler et al., 2013].

Results

TaskDatasetMetricValueModel
Interpretability Techniques for Deep LearningCelebAInsertion AUC score0.4632Saliency
Image AttributionVGGFace2Deletion AUC score (ArcFace ResNet-101)0.1907Saliency
Image AttributionVGGFace2Insertion AUC score (ArcFace ResNet-101)0.5612Saliency
Image AttributionCUB-200-2011Deletion AUC score (ResNet-101)0.0682Saliency
Image AttributionCUB-200-2011Insertion AUC score (ResNet-101)0.6585Saliency
Image AttributionCelebADeletion AUC score (ArcFace ResNet-101)0.1453Saliency
Image AttributionCelebAInsertion AUC score (ArcFace ResNet-101)0.4632Saliency

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations2025-07-18Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy2025-07-17Federated Learning for Commercial Image Sources2025-07-17MUPAX: Multidimensional Problem Agnostic eXplainable AI2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17