ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
Deep neural networks (DNNs) achieve state-of-the-art performance in many vision tasks, yet understanding their internal behavior remains challenging, particularly how different layers and activation channels contribute to class separability. We introduce ChannelExplorer, an interactive visual analytics tool for analyzing image-based outputs across model layers, emphasizing data-driven insights over architecture analysis for exploring class separability. ChannelExplorer summarizes activations across layers and visualizes them using three primary coordinated views: a Scatterplot View to reveal inter- and intra-class confusion, a Jaccard Similarity View to quantify activation overlap, and a Heatmap View to inspect activation channel patterns. Our technique supports diverse model architectures, including CNNs, GANs, ResNet and Stable Diffusion models. We demonstrate the capabilities of ChannelExplorer through four use-case scenarios: (1) generating class hierarchy in ImageNet, (2) finding mislabeled images, (3) identifying activation channel contributions, and(4) locating latent states' position in Stable Diffusion model. Finally, we evaluate the tool with expert users.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 40 of its 90 references that are in the map. First posted on arXiv 6 May 2025.
Builds on
40 of 90 references.
References · 40
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2022A ConvNet for the 2020scited by 3,545
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
- 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
- 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
28 more
- 2017Self-Normalizing Neural Networkscited by 591
- 2015Understanding Neural Networks Through Deep Visualizationcited by 332
- 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
- 2020Hyper-Parameter Optimization: A Review of Algorithms and Applicationscited by 114
- 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
- 2017Do Convolutional Neural Networks Learn Class Hierarchy?cited by 61
- 2020CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualizationcited by 57
- 2017ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Modelscited by 56
- 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 40
- 2020Analyzing the Noise Robustness of Deep Neural Networkscited by 31
- 2020Evolution of Image Segmentation using Deep Convolutional Neural Network: A Surveycited by 28
- 2015When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognitioncited by 20
- 2022ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspectivecited by 18
- 2021Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labelscited by 17
- 2023Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusioncited by 17
- 2019ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusioncited by 15
- 2018Totally Looks Like - How Humans Compare, Compared to Machinescited by 12
- 2020Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networkscited by 12
- 2024Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentationcited by 9
- 2023CLAMS: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clusteringcited by 8
- 2017CNNComparator: Comparative Analytics of Convolutional Neural Networkscited by 7
- 2019G-softmax: Improving Intra-class Compactness and Inter-class Separability of Featurescited by 6
- 2018Building Efficient ConvNets using Redundant Feature Pruningcited by 5
- 2020InstanceFlow: Visualizing the Evolution of Classifier Confusion on the Instance Levelcited by 5
- 2021LossPlot: A Better Way to Visualize Loss Landscapescited by 5
- 2021From Tinkering to Engineering: Measurements in Tensorflow Playgroundcited by 2
- 2022Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Toolscited by 1
- 2022A classification performance evaluation measure considering data separabilitycited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025TextCAM: Explaining Class Activation Map with Text
- 2026DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
- 2024Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
- 2022Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Paper
- 2025DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
- 2026Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
- 2023Diffusion Models Beat GANs on Image Classification
- 2023Dynamic Perceiver for Efficient Visual Recognition