Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yining, Sun, Junjie, Wang, Chenyue, Zhang, Mi, Yang, Min
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
di: Wang, Yining, et al.
Pubblicazione: (2025)

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

Robust Emotion Recognition in Context Debiasing
di: Yang, Dingkang, et al.
Pubblicazione: (2024)

Looking at Model Debiasing through the Lens of Anomaly Detection
di: Pastore, Vito Paolo, et al.
Pubblicazione: (2024)

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

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
di: Zhang, Yiming, et al.
Pubblicazione: (2024)

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

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

Scalable Class-Incremental Learning Based on Parametric Neural Collapse
di: Zhang, Chuangxin, et al.
Pubblicazione: (2025)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2026)

Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
di: Zhang, Xin, et al.
Pubblicazione: (2025)

Gradient Extrapolation for Debiased Representation Learning
di: Asaad, Ihab, et al.
Pubblicazione: (2025)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
di: Liu, Gongye, et al.
Pubblicazione: (2023)

All-around Neural Collapse for Imbalanced Classification
di: Zhang, Enhao, et al.
Pubblicazione: (2024)

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
di: Kuhn, Lukas, et al.
Pubblicazione: (2025)

Rethinking Meta-Learning from a Learning Lens
di: Wang, Jingyao, et al.
Pubblicazione: (2024)

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

Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution
di: Kuang, Peng, et al.
Pubblicazione: (2024)

Debiasing Vison-Language Models with Text-Only Training
di: Yang, Yunfan, et al.
Pubblicazione: (2024)

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
di: Hong, Jinyung, et al.
Pubblicazione: (2024)

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

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

Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
di: Goel, Atharv, et al.
Pubblicazione: (2025)

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

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

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

Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing
di: Fang, Zihan, et al.
Pubblicazione: (2025)

Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model
di: Huang, Lin-Chun, et al.
Pubblicazione: (2025)

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

Meta ControlNet: Enhancing Task Adaptation via Meta Learning
di: Yang, Junjie, et al.
Pubblicazione: (2023)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
di: Dehdashtian, Sepehr, et al.
Pubblicazione: (2024)

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

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

BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
di: Wang, Yuanchao, et al.
Pubblicazione: (2025)

Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning
di: Wang, Chendi, et al.
Pubblicazione: (2024)

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
di: Cai, Xu, et al.
Pubblicazione: (2025)

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

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

Model Debiasing by Learnable Data Augmentation
di: Morerio, Pietro, et al.
Pubblicazione: (2024)

Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network
di: Liu, Houze, et al.
Pubblicazione: (2024)