Copertina

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Jeeyung, Wang, Ze, Qiu, Qiang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Model-Agnostic Human Preference Inversion in Diffusion Models
di: Kim, Jeeyung, et al.
Pubblicazione: (2024)

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps
di: Kim, Jeeyung, et al.
Pubblicazione: (2024)

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

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

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

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
di: Huang, Gaoxiang, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
di: Toubal, Imad Eddine, et al.
Pubblicazione: (2024)

SLIM: Spuriousness Mitigation with Minimal Human Annotations
di: Xuan, Xiwei, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

EMA: Effort Metric Attention for Anatomical Effort-Guided Human Motion Diffusion
di: Siy, Joshua, et al.
Pubblicazione: (2026)

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

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

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

Mitigating Bias in Concept Bottleneck Models for Fair and Interpretable Image Classification
di: Tong, Schrasing, et al.
Pubblicazione: (2026)

Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
di: Pahde, Frederik, 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)

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
di: Nielen, Tim, et al.
Pubblicazione: (2026)

Focusing Image Generation to Mitigate Spurious Correlations
di: Li, Xuewei, et al.
Pubblicazione: (2024)

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

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

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

MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
di: Ye, Wenqian, et al.
Pubblicazione: (2024)

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
di: Yang, Yu, et al.
Pubblicazione: (2023)

Large Convolutional Model Tuning via Filter Subspace
di: Chen, Wei, et al.
Pubblicazione: (2024)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
di: Wu, Yongliang, et al.
Pubblicazione: (2024)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
di: Guo, Zirun, et al.
Pubblicazione: (2025)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
di: Liu, Hui, et al.
Pubblicazione: (2025)