Imagen de Portada

Vision Transformer Finetuning Benefits from Non-Smooth Components

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Odonnat, Ambroise, Chapel, Laetitia, Tavenard, Romain, Redko, Ievgen
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Layer by layer, module by module: Choose both for optimal OOD probing of ViT
por: Odonnat, Ambroise, et al.
Publicado: (2026)

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
por: Roschmann, Simon, et al.
Publicado: (2025)

Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
por: Odonnat, Ambroise, et al.
Publicado: (2023)

Differentiable Generalized Sliced Wasserstein Plans
por: Chapel, Laetitia, et al.
Publicado: (2025)

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
por: Liu, Haoyang, et al.
Publicado: (2024)

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
por: Ilbert, Romain, et al.
Publicado: (2024)

Large Language Models as Markov Chains
por: Zekri, Oussama, et al.
Publicado: (2024)

Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers
por: Li, Zeyu Michael
Publicado: (2024)

Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
por: Xie, Renchunzi, et al.
Publicado: (2024)

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
por: Ilbert, Romain, et al.
Publicado: (2024)

OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging
por: Han, Zihao, et al.
Publicado: (2025)

Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
por: Pinto, Juliano, et al.
Publicado: (2023)

When Does Perceptual Alignment Benefit Vision Representations?
por: Sundaram, Shobhita, et al.
Publicado: (2024)

Unified Vision-Language Modeling via Concept Space Alignment
por: Qiu, Yifu, et al.
Publicado: (2026)

Finetuning CLIP to Reason about Pairwise Differences
por: Sam, Dylan, et al.
Publicado: (2024)

Revisiting Mixout: An Overlooked Path to Robust Finetuning
por: Aminbeidokhti, Masih, et al.
Publicado: (2025)

Mechanisms of Non-Monotonic Scaling in Vision Transformers
por: Kumar, Anantha Padmanaban Krishna
Publicado: (2025)

Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge
por: Eliopoulos, Nick John, et al.
Publicado: (2024)

Native Segmentation Vision Transformers
por: Brasó, Guillem, et al.
Publicado: (2025)

Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
por: Tian, Hongduan, et al.
Publicado: (2024)

Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows
por: Huo, Simin, et al.
Publicado: (2025)

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks
por: Dhakal, Manish, et al.
Publicado: (2024)

RAViT: Resolution-Adaptive Vision Transformer
por: Guidez, Martial, et al.
Publicado: (2026)

Slicing Vision Transformer for Flexible Inference
por: Zhang, Yitian, et al.
Publicado: (2024)

Rotary Position Embedding for Vision Transformer
por: Heo, Byeongho, et al.
Publicado: (2024)

Decorrelation Speeds Up Vision Transformers
por: Carrigg, Kieran, et al.
Publicado: (2025)

Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework
por: Zheng, Jingjing, et al.
Publicado: (2023)

How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey
por: Qi, Yayun, et al.
Publicado: (2024)

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
por: Zhong, Zihan, et al.
Publicado: (2024)

Elastic Attention Cores for Scalable Vision Transformers
por: Song, Alan Z., et al.
Publicado: (2026)

Attention Transfer Is Not Universally Effective for Vision Transformers
por: Qin, Huaiyuan, et al.
Publicado: (2026)

SPoT: Subpixel Placement of Tokens in Vision Transformers
por: Hjelkrem-Tan, Martine, et al.
Publicado: (2025)

Instance-Aware Group Quantization for Vision Transformers
por: Moon, Jaehyeon, et al.
Publicado: (2024)

Vision Transformer-based Adversarial Domain Adaptation
por: Li, Yahan, et al.
Publicado: (2024)

Compact Vision Transformer by Reduction of Kernel Complexity
por: Wang, Yancheng, et al.
Publicado: (2025)

Split Adaptation for Pre-trained Vision Transformers
por: Wang, Lixu, et al.
Publicado: (2025)

DASViT: Differentiable Architecture Search for Vision Transformer
por: Wu, Pengjin, et al.
Publicado: (2025)

Stable Vision Concept Transformers for Medical Diagnosis
por: Hu, Lijie, et al.
Publicado: (2025)

Self-Supervised Vision Transformers for Writer Retrieval
por: Raven, Tim, et al.
Publicado: (2024)

HEAL-SWIN: A Vision Transformer On The Sphere
por: Carlsson, Oscar, et al.
Publicado: (2023)