Cover Image

Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wickstrøm, Kristoffer, Dorszewski, Teresa, Chen, Siyan, Kampffmeyer, Michael, Wetzer, Elisabeth, Jenssen, Robert
Format:	Preprint
Published:	2025
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

Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models
by: Salahuddin, Suaiba Amina, et al.
Published: (2025)

From Colors to Classes: Emergence of Concepts in Vision Transformers
by: Dorszewski, Teresa, et al.
Published: (2025)

Fast Voxel-Wise Kinetic Modeling in Dynamic PET using a Physics-Informed CycleGAN
by: Salomonsen, Christian, et al.
Published: (2025)

The Impact of Longitudinal Mammogram Alignment on Breast Cancer Risk Assessment
by: Thrun, Solveig, et al.
Published: (2025)

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction
by: Thrun, Solveig, et al.
Published: (2025)

Physics-Informed Deep Learning for Improved Input Function Estimation in Motion-Blurred Dynamic [${}^{18}$F]FDG PET Images
by: Salomonsen, Christian, et al.
Published: (2025)

A robust and versatile deep learning model for prediction of the arterial input function in dynamic small animal $\left[^{18}\text{F}\right]$FDG PET imaging
by: Salomonsen, Christian, et al.
Published: (2025)

Random Window Augmentations for Deep Learning Robustness in CT and Liver Tumor Segmentation
by: Østmo, Eirik A., et al.
Published: (2025)

SuperCM: Improving Semi-Supervised Learning and Domain Adaptation through differentiable clustering
by: Singh, Durgesh, et al.
Published: (2025)

REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability
by: Wickstrøm, Kristoffer K., et al.
Published: (2024)

Leveraging tensor kernels to reduce objective function mismatch in deep clustering
by: Trosten, Daniel J., et al.
Published: (2020)

Supercm: Revisiting Clustering for Semi-Supervised Learning
by: Singh, Durgesh, et al.
Published: (2025)

WiseLVAM: A Novel Framework For Left Ventricle Automatic Measurements
by: Singh, Durgesh Kumar, et al.
Published: (2025)

EnLVAM: Enhanced Left Ventricle Linear Measurements Utilizing Anatomical Motion Mode
by: Singh, Durgesh K., et al.
Published: (2025)

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
by: Chakraborty, Rwiddhi, et al.
Published: (2024)

Learning to Adapt to Position Bias in Vision Transformer Classifiers
by: Bruintjes, Robert-Jan, et al.
Published: (2025)

SYNCS: Synthetic Data and Contrastive Self-Supervised Training for Central Sulcus Segmentation
by: Zalevskyi, Vladyslav, et al.
Published: (2024)

In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
by: Corbetta, Valentina, et al.
Published: (2025)

Identification of Conversation Partners from Egocentric Video
by: Dorszewski, Tobias, et al.
Published: (2024)

Tied Prototype Model for Few-Shot Medical Image Segmentation
by: Kim, Hyeongji, et al.
Published: (2025)

Model Guidance via Explanations Turns Image Classifiers into Segmentation Models
by: Yu, Xiaoyan, et al.
Published: (2024)

Evaluating the Explainability of Vision Transformers in Medical Imaging
by: Barekatain, Leili, et al.
Published: (2025)

ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval
by: Pan, Yi, et al.
Published: (2025)

Decision-Aware Attention Propagation for Vision Transformer Explainability
by: Jo, Sehyeong, et al.
Published: (2026)

SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes
by: Zohaib, Mohammad, et al.
Published: (2024)

LatentKeypointGAN: Controlling Images via Latent Keypoints
by: He, Xingzhe, et al.
Published: (2021)

DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion Models
by: Sarmad, Muhammad, et al.
Published: (2025)

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
by: Liu, Shuming, et al.
Published: (2025)

Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
by: Yang, Yijie, et al.
Published: (2024)

Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision
by: Khalil, Daniel, et al.
Published: (2024)

Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
by: Duangprom, Krit, et al.
Published: (2025)

Lossless Token Merging Even Without Fine-Tuning in Vision Transformers
by: Lee, Jaeyeon, et al.
Published: (2025)

Unsupervised Keypoints from Pretrained Diffusion Models
by: Hedlin, Eric, et al.
Published: (2023)

VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction
by: Sun, Zijun, et al.
Published: (2025)

Explainable Part-Based Vehicle Classifier with Spatial Awareness
by: Caduff, Andreas, et al.
Published: (2026)

Unleashing Guidance Without Classifiers for Human-Object Interaction Animation
by: Wang, Ziyin, et al.
Published: (2026)

On the Explainability of Vision-Language Models in Art History
by: Schneider, Stefanie
Published: (2026)

Explainability for Vision Foundation Models: A Survey
by: Kazmierczak, Rémi, et al.
Published: (2025)

Vision Transformers with Self-Distilled Registers
by: Chen, Yinjie, et al.
Published: (2025)

Keypoint Promptable Re-Identification
by: Somers, Vladimir, et al.
Published: (2024)