Image de couverture de livre

Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chamas, Rabih, Khalfaoui-Hassani, Ismail, Masquelier, Timothee
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
par: Hammouamri, Ilyass, et autres
Publié: (2023)

Dilated Convolution with Learnable Spacings
par: Khalfaoui-Hassani, Ismail
Publié: (2024)

Polynomial, trigonometric, and tropical activations
par: Khalfaoui-Hassani, Ismail, et autres
Publié: (2025)

Self-supervised video pretraining yields robust and more human-aligned visual representations
par: Parthasarathy, Nikhil, et autres
Publié: (2022)

An Attention Infused Deep Learning System with Grad-CAM Visualization for Early Screening of Glaucoma
par: Swaminathan, Ramanathan
Publié: (2025)

Weakly Supervised Pneumonia Localization from Chest X-Rays Using Deep Neural Network and Grad-CAM Explanations
par: Shahi, Kiran, et autres
Publié: (2025)

Toward Reliable and Explainable Nail Disease Classification: Leveraging Adversarial Training and Grad-CAM Visualization
par: Hossain, Farzia, et autres
Publié: (2026)

RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone
par: Munir, Mustafa, et autres
Publié: (2024)

A Clinically Interpretable Deep CNN Framework for Early Chronic Kidney Disease Prediction Using Grad-CAM-Based Explainable AI
par: Ayub, Anas Bin, et autres
Publié: (2025)

Enhancing Satellite Object Localization with Dilated Convolutions and Attention-aided Spatial Pooling
par: Mostafa, Seraj Al Mahmud, et autres
Publié: (2025)

Vision Transformer attention alignment with human visual perception in aesthetic object evaluation
par: Carrasco, Miguel, et autres
Publié: (2025)

Enhanced SegNet with Integrated Grad-CAM for Interpretable Retinal Layer Segmentation in OCT Images
par: Saky, S M Asiful Islam, et autres
Publié: (2025)

Explainable Image Similarity: Integrating Siamese Networks and Grad-CAM
par: Livieris, Ioannis E., et autres
Publié: (2023)

Quantifying the human visual exposome with vision language models
par: Rominger, Christian, et autres
Publié: (2026)

Reimagining Linear Probing: Kolmogorov-Arnold Networks in Transfer Learning
par: Shen, Sheng, et autres
Publié: (2024)

DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
par: Liu, Xuewen, et autres
Publié: (2024)

A Cascaded Dilated Convolution Approach for Mpox Lesion Classification
par: Deshmukh, Ayush
Publié: (2024)

MARS: Paying more attention to visual attributes for text-based person search
par: Ergasti, Alex, et autres
Publié: (2024)

DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
par: Lyu, Yueming, et autres
Publié: (2023)

How to Evaluate and Refine your CAM
par: Domeniconi, Luca, et autres
Publié: (2026)

Towards aligned body representations in vision models
par: Gizdov, Andrey, et autres
Publié: (2025)

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy
par: Kawano, Keisuke, et autres
Publié: (2024)

Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
par: Pan, Shuokai, et autres
Publié: (2024)

Explaining generative diffusion models via visual analysis for interpretable decision-making process
par: Park, Ji-Hoon, et autres
Publié: (2024)

Generalizing GradCAM for Embedding Networks
par: Bachhawat, Mudit
Publié: (2024)

Improving generalization by mimicking the human visual diet
par: Madan, Spandan, et autres
Publié: (2022)

Med-CAM: Minimal Evidence for Explaining Medical Decision Making
par: Suhail, Pirzada, et autres
Publié: (2026)

Integrative CAM: Adaptive Layer Fusion for Comprehensive Interpretation of CNNs
par: Singh, Aniket K., et autres
Publié: (2024)

CAM-VFD: Cross-Attention Multimodal Video Forgery Detection
par: Elkhodary, Hoda Osama, et autres
Publié: (2026)

Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!
par: Chung, Jiwan, et autres
Publié: (2024)

Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
par: Zhang, Ziheng, et autres
Publié: (2025)

Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
par: Chowdhury, Arpita, et autres
Publié: (2025)

Feature CAM: Interpretable AI in Image Classification
par: Clement, Frincy, et autres
Publié: (2024)

Implicit Deformable Medical Image Registration with Learnable Kernels
par: Fogarollo, Stefano, et autres
Publié: (2025)

Deep learning models are vulnerable, but adversarial examples are even more vulnerable
par: Li, Jun, et autres
Publié: (2025)

PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilation
par: Liang, Ao, et autres
Publié: (2025)

CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image Generation
par: Ahmed, Masud, et autres
Publié: (2025)

EmoCAM: Toward Understanding What Drives CNN-based Emotion Recognition
par: Doulfoukar, Youssef, et autres
Publié: (2024)

Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention
par: Leem, Saebom, et autres
Publié: (2024)

VLA-Mark: A cross modal watermark for large vision-language alignment model
par: Liu, Shuliang, et autres
Publié: (2025)