Image de couverture de livre

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Noohdani, Fahimeh Hosseini, Hosseini, Parsa, Parast, Aryan Yazdan, Araghi, Hamidreza Yaghoubi, Baghshah, Mahdieh Soleymani
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation
par: Ghaznavi, Mahdi, et autres
Publié: (2024)

Dilated Balanced Cross Entropy Loss for Medical Image Segmentation
par: Hosseini, Seyed Mohsen, et autres
Publié: (2024)

DDB: Diffusion Driven Balancing to Address Spurious Correlations
par: Parast, Aryan Yazdan, et autres
Publié: (2025)

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
par: Parast, Aryan Yazdan, et autres
Publié: (2025)

Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
par: Zohrabi, Reihaneh, et autres
Publié: (2025)

Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
par: Izadi, Amir Mohammad, et autres
Publié: (2025)

Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning Method
par: Sani, Matina Mahdizadeh, et autres
Publié: (2024)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
par: Abbasi, Reza, et autres
Publié: (2024)

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
par: Zohrabi, Reihaneh, et autres
Publié: (2026)

HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations
par: Parast, Aryan Yazdan, et autres
Publié: (2026)

LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
par: Mehri, Faridoun, et autres
Publié: (2024)

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs
par: Hosseini, Parsa, et autres
Publié: (2025)

T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation
par: Hosseini, Seyed Mohammad Hadi, et autres
Publié: (2025)

Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labeling
par: Mozafari, Mohammad, et autres
Publié: (2024)

Unsupervised Concept Discovery Mitigates Spurious Correlations
par: Arefin, Md Rifat, et autres
Publié: (2024)

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
par: Abbasi, Reza, et autres
Publié: (2024)

SUSD: Structured Unsupervised Skill Discovery through State Factorization
par: Hosseini, Seyed Mohammad Hadi, et autres
Publié: (2026)

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
par: Zheng, Guangtao, et autres
Publié: (2024)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
par: Liu, Chenruo, et autres
Publié: (2025)

Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
par: Kim, Jeeyung, et autres
Publié: (2024)

Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
par: Marioriyad, Arash, et autres
Publié: (2024)

MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations
par: Jin, Qixuan, et autres
Publié: (2024)

CER: Confidence Enhanced Reasoning in LLMs
par: Razghandi, Ali, et autres
Publié: (2025)

Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs
par: Izadi, Amirmohammad, et autres
Publié: (2025)

Imbalanced Classification through the Lens of Spurious Correlations
par: Hackstein, Jakob, et autres
Publié: (2025)

Revolutionizing Traffic Management with AI-Powered Machine Vision: A Step Toward Smart Cities
par: DolatAbadi, Seyed Hossein Hosseini, et autres
Publié: (2025)

Efficient Adversarial Attacks on High-dimensional Offline Bandits
par: Hosseini, Seyed Mohammad Hadi, et autres
Publié: (2026)

Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models
par: Shahabadi, Hossein, et autres
Publié: (2025)

UnLearning from Experience to Avoid Spurious Correlations
par: Mitchell, Jeff, et autres
Publié: (2024)

The Impact of Coreset Selection on Spurious Correlations and Group Robustness
par: Dharmasiri, Amaya, et autres
Publié: (2025)

RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
par: Mirzaei, Hossein, et autres
Publié: (2025)

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
par: Hasanebrahimi, Afsaneh, et autres
Publié: (2026)

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
par: Kim, Nayeong, et autres
Publié: (2024)

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
par: Huang, Gaoxiang, et autres
Publié: (2025)

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation
par: Puli, Aahlad, et autres
Publié: (2022)

Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
par: Le, Phuong Quynh, et autres
Publié: (2023)

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
par: Rezaei, Parham, et autres
Publié: (2025)

Identifying Spurious Correlations using Counterfactual Alignment
par: Cohen, Joseph Paul, et autres
Publié: (2023)

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
par: Chakraborty, Rwiddhi, et autres
Publié: (2024)

Pixel-wise Modulated Dice Loss for Medical Image Segmentation
par: Hosseini, Seyed Mohsen
Publié: (2025)