Cover Image

Metonymy in vision models undermines attention-based interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aniraj, Ananthu, Dantas, Cassio F., Ienco, Dino, Mancini, Massimiliano, Marcos, Diego
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
by: Aniraj, Ananthu, et al.
Published: (2025)

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers
by: Aniraj, Ananthu, et al.
Published: (2024)

DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning
by: Ienco, Dino, et al.
Published: (2024)

Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation
by: Ferrod, Roger, et al.
Published: (2025)

Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
by: Mena, Francisco, et al.
Published: (2025)

SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
by: Jain, Pallavi, et al.
Published: (2024)

TimeSenCLIP: A Time Series Vision-Language Model for Remote Sensing
by: Jain, Pallavi, et al.
Published: (2025)

Geographical Context Matters: Bridging Fine and Coarse Spatial Information to Enhance Continental Land Cover Mapping
by: Ghassemi, Babak, et al.
Published: (2025)

Towards a multimodal framework for remote sensing image change retrieval and captioning
by: Ferrod, Roger, et al.
Published: (2024)

RAMEN: Resolution-Adjustable Multimodal Encoder for Earth Observation
by: Houdré, Nicolas, et al.
Published: (2025)

A Computational Approach to Visual Metonymy
by: Ghosh, Saptarshi, et al.
Published: (2026)

A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism
by: Zheng, Peng, et al.
Published: (2024)

Vision-by-Language for Training-Free Compositional Image Retrieval
by: Karthik, Shyamgopal, et al.
Published: (2023)

The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
by: Caldarella, Simone, et al.
Published: (2024)

Addressing a fundamental limitation in deep vision models: lack of spatial attention
by: Borji, Ali
Published: (2024)

Cross-attention for State-based model RWKV-7
by: Xiao, Liu, et al.
Published: (2025)

an interpretable vision transformer framework for automated brain tumor classification
by: Mbonu, Chinedu Emmanuel, et al.
Published: (2026)

Low-latency vision transformers via large-scale multi-head attention
by: Gross, Ronit D., et al.
Published: (2025)

Large Multimodal Models as General In-Context Classifiers
by: Garosi, Marco, et al.
Published: (2026)

One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering
by: Das, Deepayan, et al.
Published: (2024)

Training-Free Personalization via Retrieval and Reasoning on Fingerprints
by: Das, Deepayan, et al.
Published: (2025)

Compositional Caching for Training-free Open-vocabulary Attribute Detection
by: Garosi, Marco, et al.
Published: (2025)

Harnessing Large Language Models for Training-free Video Anomaly Detection
by: Zanella, Luca, et al.
Published: (2024)

Training-free Online Video Step Grounding
by: Zanella, Luca, et al.
Published: (2025)

Deep spatial context: when attention-based models meet spatial regression
by: Tomaszewska, Paulina, et al.
Published: (2024)

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
by: De Min, Thomas, et al.
Published: (2026)

Unlearning Personal Data from a Single Image
by: De Min, Thomas, et al.
Published: (2024)

Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
by: Huang, Yiran, et al.
Published: (2025)

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
by: Farina, Matteo, et al.
Published: (2024)

Vocabulary-free Image Classification and Semantic Segmentation
by: Conti, Alessandro, et al.
Published: (2024)

Vocabulary-free Image Classification
by: Conti, Alessandro, et al.
Published: (2023)

3D Part Segmentation via Geometric Aggregation of 2D Visual Features
by: Garosi, Marco, et al.
Published: (2024)

Can Text-to-Video Generation help Video-Language Alignment?
by: Zanella, Luca, et al.
Published: (2025)

On Large Multimodal Models as Open-World Image Classifiers
by: Conti, Alessandro, et al.
Published: (2025)

Automatic benchmarking of large multimodal models via iterative experiment programming
by: Conti, Alessandro, et al.
Published: (2024)

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
by: Gentile, Francesco, et al.
Published: (2026)

Test-time Vocabulary Adaptation for Language-driven Object Detection
by: Liu, Mingxuan, et al.
Published: (2025)

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
by: D'Incà, Moreno, et al.
Published: (2024)

Fused attention mechanism-based ore sorting network
by: Zhen, Junjiang, et al.
Published: (2024)

PSO-Net: Development of an automated psoriasis assessment system using attention-based interpretable deep neural networks
by: Kamran, Sharif A., et al.
Published: (2025)