Copertina

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Elisha, Yehonatan, Barkan, Oren, Koenigstein, Noam
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
di: Elisha, Yehonatan, et al.
Pubblicazione: (2025)

BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation
di: Barkan, Oren, et al.
Pubblicazione: (2024)

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems
di: Arviv, Dor, et al.
Pubblicazione: (2025)

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
di: Barkan, Oren, et al.
Pubblicazione: (2025)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
di: Shah, Arya, et al.
Pubblicazione: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
di: Heo, Jung Hwan, et al.
Pubblicazione: (2023)

Octic Vision Transformers: Quicker ViTs Through Equivariance
di: Nordström, David, et al.
Pubblicazione: (2025)

ConcatPlexer: Additional Dim1 Batching for Faster ViTs
di: Han, Donghoon, et al.
Pubblicazione: (2023)

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
di: Wang, Zhibo, et al.
Pubblicazione: (2026)

Communication Efficient Split Learning of ViTs with Attention-based Double Compression
di: Alvetreti, Federico, et al.
Pubblicazione: (2025)

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
di: Ramachandran, Akshat, et al.
Pubblicazione: (2024)

VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTs
di: Wang, Xiyao, et al.
Pubblicazione: (2026)

ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain
di: Mia, Md Sohag, et al.
Pubblicazione: (2023)

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
di: Chen, Lu, et al.
Pubblicazione: (2025)

HydraViT: Stacking Heads for a Scalable ViT
di: Haberer, Janek, et al.
Pubblicazione: (2024)

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

STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs
di: Chattopadhyay, Nandish, et al.
Pubblicazione: (2026)

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

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

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

MobilePlantViT: A Mobile-friendly Hybrid ViT for Generalized Plant Disease Image Classification
di: Tonmoy, Moshiur Rahman, et al.
Pubblicazione: (2025)

Token Cropr: Faster ViTs for Quite a Few Tasks
di: Bergner, Benjamin, et al.
Pubblicazione: (2024)

DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
di: Tong, Yujia, et al.
Pubblicazione: (2025)

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

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
di: Li, Zhengang, et al.
Pubblicazione: (2024)

Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels
di: Marrium, Maria, et al.
Pubblicazione: (2024)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
di: Hwang, Dongyoon, et al.
Pubblicazione: (2024)

Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks
di: Khanal, Aja, et al.
Pubblicazione: (2025)

ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
di: Mutlu, Abdulvahap, 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)

Selective Fine-Tuning for Targeted and Robust Concept Unlearning
di: Mansi, et al.
Pubblicazione: (2026)

ViT-Lens: Towards Omni-modal Representations
di: Lei, Weixian, et al.
Pubblicazione: (2023)

Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
di: Yunusa, Haruna, et al.
Pubblicazione: (2024)

Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
di: Huang, Lianghuan, et al.
Pubblicazione: (2025)

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
di: Zhong, Yunshan, et al.
Pubblicazione: (2023)

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
di: Aggarwal, Aarush, et al.
Pubblicazione: (2026)

SFMViT: SlowFast Meet ViT in Chaotic World
di: Lin, Jiaying, et al.
Pubblicazione: (2024)

MMeViT: Multi-Modal ensemble ViT for Post-Stroke Rehabilitation Action Recognition
di: Kim, Ye-eun, et al.
Pubblicazione: (2025)

DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
di: Wróbel, Adam, et al.
Pubblicazione: (2026)

Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
di: Bafghi, Reza Akbarian, et al.
Pubblicazione: (2024)