Copertina

Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Delzer, Ole, Bender, Sidney
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Debiasing surgeon: fantastic weights and how to find them
di: Nahon, Rémi, et al.
Pubblicazione: (2024)

Imbalanced Classification through the Lens of Spurious Correlations
di: Hackstein, Jakob, et al.
Pubblicazione: (2025)

MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis
di: Fay, Louisa, et al.
Pubblicazione: (2025)

Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
di: Kang, Solha, et al.
Pubblicazione: (2025)

CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation
di: Govindarajan, Hariprasath, et al.
Pubblicazione: (2025)

Identifying Spurious Correlations using Counterfactual Alignment
di: Cohen, Joseph Paul, et al.
Pubblicazione: (2023)

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility
di: Barsbey, Melih, et al.
Pubblicazione: (2025)

Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation
di: Ghaznavi, Mahdi, et al.
Pubblicazione: (2024)

GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning
di: Kim, Nayeong, et al.
Pubblicazione: (2025)

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
di: Varma, Maya, et al.
Pubblicazione: (2024)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
di: Liu, Chenruo, et al.
Pubblicazione: (2025)

Preventing Shortcuts in Adapter Training via Providing the Shortcuts
di: Goyal, Anujraaj Argo, et al.
Pubblicazione: (2025)

QueensCAMP: an RGB-D dataset for robust Visual SLAM
di: Bruno, Hudson M. S., et al.
Pubblicazione: (2024)

Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning
di: Bleeker, Maurits, et al.
Pubblicazione: (2024)

BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision
di: Bransby, Kit Mills, et al.
Pubblicazione: (2024)

Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
di: Bender, Sidney, et al.
Pubblicazione: (2025)

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
di: Ghosh, Sreyan, et al.
Pubblicazione: (2023)

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
di: Kwon, JuneHyoung, et al.
Pubblicazione: (2024)

Uncovering Memorization Effect in the Presence of Spurious Correlations
di: You, Chenyu, et al.
Pubblicazione: (2025)

Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
di: Wang, Yihui, et al.
Pubblicazione: (2026)

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
di: Elisha, Yehonatan, et al.
Pubblicazione: (2026)

Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
di: Xing, Youguang, et al.
Pubblicazione: (2025)

SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
di: Ye, Wenqian, et al.
Pubblicazione: (2025)

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

Audio-centric Video Understanding Benchmark without Text Shortcut
di: Yang, Yudong, et al.
Pubblicazione: (2025)

Preventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
di: Boland, Christopher, et al.
Pubblicazione: (2025)

Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records
di: Kim, Seorin, et al.
Pubblicazione: (2025)

Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models
di: Zhang, Jingrui, et al.
Pubblicazione: (2026)

The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
di: Hu, Xia, et al.
Pubblicazione: (2026)

Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables
di: Hinns, James, et al.
Pubblicazione: (2024)

Spread them Apart: Towards Robust Watermarking of Generated Content
di: Pautov, Mikhail, et al.
Pubblicazione: (2025)

Using Shapley interactions to understand how models use structure
di: Singhvi, Divyansh, et al.
Pubblicazione: (2024)

SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
di: Won, Jong Bum, et al.
Pubblicazione: (2025)

Exploration of Reproducible Generated Image Detection
di: Duan, Yihang
Pubblicazione: (2025)

Invisible Attributes, Visible Biases: Exploring Demographic Shortcuts in MRI-based Alzheimer's Disease Classification
di: Achara, Akshit, et al.
Pubblicazione: (2025)

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
di: Qiao, Rui, et al.
Pubblicazione: (2025)

Taking Shortcuts for Categorical VQA Using Super Neurons
di: Musacchio, Pierre, et al.
Pubblicazione: (2026)

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
di: Narasimhaswamy, Supreeth, et al.
Pubblicazione: (2024)

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
di: Ahn, Geo, et al.
Pubblicazione: (2026)

Reliable, Routable, and Reproducible: Collection of Pedestrian Pathways at Statewide Scale
di: Zhang, Yuxiang, et al.
Pubblicazione: (2024)