Cover Image

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chakraborty, Rwiddhi, Sletten, Adrian, Kampffmeyer, Michael
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Impact of Coreset Selection on Spurious Correlations and Group Robustness
by: Dharmasiri, Amaya, et al.
Published: (2025)

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

Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning
by: Arteaga, Gabriel Y., et al.
Published: (2025)

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
by: Zheng, Guangtao, et al.
Published: (2024)

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
by: Kim, Nayeong, et al.
Published: (2024)

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

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

Robust Classification by Coupling Data Mollification with Label Smoothing
by: Heinonen, Markus, et al.
Published: (2024)

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

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

UnLearning from Experience to Avoid Spurious Correlations
by: Mitchell, Jeff, et al.
Published: (2024)

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
by: Litrico, Mattia, et al.
Published: (2025)

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

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

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
by: Noohdani, Fahimeh Hosseini, et al.
Published: (2024)

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
by: Hasanebrahimi, Afsaneh, et al.
Published: (2026)

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation
by: Puli, Aahlad, et al.
Published: (2022)

A Sober Look at the Robustness of CLIPs to Spurious Features
by: Wang, Qizhou, et al.
Published: (2024)

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
by: Kim, Jeeyung, et al.
Published: (2024)

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

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

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

MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations
by: Jin, Qixuan, et al.
Published: (2024)

From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition
by: Qraitem, Maan, et al.
Published: (2023)

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

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

Part-based Quantitative Analysis for Heatmaps
by: Tursun, Osman, et al.
Published: (2024)

Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
by: Yang, Yiwei, et al.
Published: (2025)

UM3: Unsupervised Map to Map Matching
by: Ying, Chaolong, et al.
Published: (2025)

Leveraging Expert Input for Robust and Explainable AI-Assisted Lung Cancer Detection in Chest X-rays
by: Rafferty, Amy, et al.
Published: (2024)

BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
by: Chakraborty, Rajatsubhra, et al.
Published: (2025)

Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them
by: Delzer, Ole, et al.
Published: (2026)

Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology
by: Idaji, Mina Jamshidi, et al.
Published: (2026)

SyncMapV2: Robust and Adaptive Unsupervised Segmentation
by: Zhang, Heng, et al.
Published: (2025)

Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption
by: Wakai, Nobuhiko, et al.
Published: (2023)

Benchmarking Spurious Bias in Few-Shot Image Classifiers
by: Zheng, Guangtao, et al.
Published: (2024)

CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models
by: Bouayed, Aymene Mohammed, et al.
Published: (2024)

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

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection
by: Molahasani, Mahdiyar, et al.
Published: (2025)

Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
by: Zohrabi, Reihaneh, et al.
Published: (2025)