Imagen de Portada

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kuhn, Lukas, Sadiya, Sari, Schlotterer, Jorg, Buettner, Florian, Seifert, Christin, Roig, Gemma
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Shortcut Mitigation via Spurious-Positive Samples
por: Le, Phuong Quynh, et al.
Publicado: (2026)

An XAI-based Analysis of Shortcut Learning in Neural Networks
por: Le, Phuong Quynh, et al.
Publicado: (2025)

Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
por: Le, Phuong Quynh, et al.
Publicado: (2023)

ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
por: Lyu, Kailin, et al.
Publicado: (2025)

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning
por: Dolatabadi, Hadi M., et al.
Publicado: (2024)

Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine
por: Eryılmaz, Bahadır, et al.
Publicado: (2024)

Human Gaze Boosts Object-Centered Representation Learning
por: Schaumlöffel, Timothy, et al.
Publicado: (2025)

Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
por: Müller, Sarah, et al.
Publicado: (2026)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
por: Scimeca, Luca, et al.
Publicado: (2023)

On the Foundations of Shortcut Learning
por: Hermann, Katherine L., et al.
Publicado: (2023)

Disentangling Mean Embeddings for Better Diagnostics of Image Generators
por: Gruber, Sebastian G., et al.
Publicado: (2024)

Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment
por: Kuhn, Lukas, et al.
Publicado: (2026)

Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classification
por: De Santi, Lisa Anita, et al.
Publicado: (2024)

FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
por: Panda, Mahadev Prasad, et al.
Publicado: (2024)

Shortcut Learning Susceptibility in Vision Classifiers
por: Suhail, Pirzada, et al.
Publicado: (2025)

PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
por: De Santi, Lisa Anita, et al.
Publicado: (2024)

Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges
por: Pathak, Shreyasi, et al.
Publicado: (2024)

Learning Object Semantic Similarity with Self-Supervision
por: Aubret, Arthur, et al.
Publicado: (2024)

Persuasion Tokens for Editing Factual Knowledge in LLMs
por: Youssef, Paul, et al.
Publicado: (2026)

Unsupervised Concept Discovery Mitigates Spurious Correlations
por: Arefin, Md Rifat, et al.
Publicado: (2024)

Debiasify: Self-Distillation for Unsupervised Bias Mitigation
por: Bayasi, Nourhan, et al.
Publicado: (2024)

Unsupervised Representation Learning from Sparse Transformation Analysis
por: Song, Yue, et al.
Publicado: (2024)

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
por: Li, Jiachen, et al.
Publicado: (2025)

Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging
por: Müller, Sarah, et al.
Publicado: (2024)

Case-level Breast Cancer Prediction for Real Hospital Settings
por: Pathak, Shreyasi, et al.
Publicado: (2023)

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
por: Wang, Yining, et al.
Publicado: (2024)

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
por: Jia, Haozhe, et al.
Publicado: (2026)

Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Play
por: Schaumlöffel, Timothy, et al.
Publicado: (2023)

Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization
por: Eisenhardt, Dustin, et al.
Publicado: (2026)

Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
por: Gu, Kai, et al.
Publicado: (2025)

Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
por: Vetter, Dennis, et al.
Publicado: (2024)

One Step Diffusion via Shortcut Models
por: Frans, Kevin, et al.
Publicado: (2024)

Disentangling Content from Style to Overcome Shortcut Learning: A Hybrid Generative-Discriminative Learning Framework
por: Fu, Siming, et al.
Publicado: (2025)

Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning
por: Aqeel, Muhammad, et al.
Publicado: (2025)

On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturing
por: Ren, Haoyu, et al.
Publicado: (2025)

Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams
por: Fernandes, Leonor, et al.
Publicado: (2025)

A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Study
por: Koraş, Osman Alperen, et al.
Publicado: (2024)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
por: Decker, Thomas, et al.
Publicado: (2024)

Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
por: Baker, Hassan, et al.
Publicado: (2025)

FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data
por: Im, Jiin, et al.
Publicado: (2024)