DiffGradCAM and DiffGradCAM++ use logit differences for contrastive class activation maps that resist passive fooling while matching GradCAM outputs in clean cases, tested with a new SHAM benchmark on multi-class tasks.
Axiom-based grad-cam: Towards accurate visualization and explanation of cnns
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
verdicts
UNVERDICTED 10representative citing papers
A saliency-guided wavelet framework extracts transient glitches from gravitational-wave strain data by pre-tagging candidates with UMAP, identifying time-frequency regions on CWT spectrograms, and enabling exact reconstruction via adaptive DWT coefficient masking.
XtrAIn shifts occlusion from input space to parameter space along the training trajectory to produce cleaner feature attributions than standard methods.
TEVI applies sparse autoencoders and caption-conditioned masking to edit image embeddings, yielding better retrieval on MS COCO, Flickr, IIW, DOCCI, and RoCOCO benchmarks with larger gains on richer captions.
A claimed mathematical proof establishes a quadrilemma showing that complex environments, high AI performance, interpretable explanations, and complete faithfulness cannot coexist.
FOCUS enables reliable spatial-spectral interpretability for frozen ViTs in hyperspectral imaging with class-specific prompts and a [SINK] token that reduces attention collapse.
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
Manhattan and Correlation distance metrics best align CAM saliency maps with human perception on ImageNet chihuahuas, ranking LayerCAM, Score-CAM, and IS-CAM highest when compared to crowdsourced choices via RBO.
XAI analysis identifies high visual similarity across colony cardinality classes as the primary limit on MicrobiaNet performance in bacterial colony counting, revising prior model assessments.
FM-G-CAM extends Grad-CAM by fusing explanations across multiple top classes for holistic CNN prediction understanding and ships an open-source library.
citing papers explorer
-
DiffGradCAM: A Class Activation Map Using the Full Model Decision to Solve Unaddressed Adversarial Attacks
DiffGradCAM and DiffGradCAM++ use logit differences for contrastive class activation maps that resist passive fooling while matching GradCAM outputs in clean cases, tested with a new SHAM benchmark on multi-class tasks.
-
Wavelet-Based Extraction of Transient Noise in Gravitational-Wave Interferometers using a Saliency-Guided Learning Architecture
A saliency-guided wavelet framework extracts transient glitches from gravitational-wave strain data by pre-tagging candidates with UMAP, identifying time-frequency regions on CWT spectrograms, and enabling exact reconstruction via adaptive DWT coefficient masking.
-
XtrAIn: Training-Guided Occlusion for Feature Attribution
XtrAIn shifts occlusion from input space to parameter space along the training trajectory to produce cleaner feature attributions than standard methods.
-
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
TEVI applies sparse autoencoders and caption-conditioned masking to edit image embeddings, yielding better retrieval on MS COCO, Flickr, IIW, DOCCI, and RoCOCO benchmarks with larger gains on richer captions.
-
Fundamental Limitation in Explaining AI
A claimed mathematical proof establishes a quadrilemma showing that complex environments, high AI performance, interpretable explanations, and complete faithfulness cannot coexist.
-
FOCUS: Fused Observation of Channels for Unveiling Spectra
FOCUS enables reliable spatial-spectral interpretability for frozen ViTs in hyperspectral imaging with class-specific prompts and a [SINK] token that reduces attention collapse.
-
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
Researchers train AI detectors on a large photorealistic fake image dataset, apply 16 XAI methods, and use human survey feedback to assess alignment between machine explanations and human perception of AI-generated images.
-
How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?
Manhattan and Correlation distance metrics best align CAM saliency maps with human perception on ImageNet chihuahuas, ranking LayerCAM, Score-CAM, and IS-CAM highest when compared to crowdsourced choices via RBO.
-
Investigation of cardinality classification for bacterial colony counting using explainable artificial intelligence
XAI analysis identifies high visual similarity across colony cardinality classes as the primary limit on MicrobiaNet performance in bacterial colony counting, revising prior model assessments.
-
FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision
FM-G-CAM extends Grad-CAM by fusing explanations across multiple top classes for holistic CNN prediction understanding and ships an open-source library.