Imagen de Portada

Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Méndez, David, Confalonieri, Roberto, Rodríguez, Natalia Díaz
Formato:	Preprint
Publicado:	2026
Materias:	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

CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
por: Méndez, David, et al.
Publicado: (2025)

DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
por: Ali, Eman, et al.
Publicado: (2024)

Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
por: Zhang, Yuhang, et al.
Publicado: (2025)

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs
por: Kuzucu, Selim, et al.
Publicado: (2025)

Dataset Distillation via Vision-Language Category Prototype
por: Zou, Yawen, et al.
Publicado: (2025)

Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation
por: Liu, Jie, et al.
Publicado: (2025)

Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment
por: Gou, Dongqiang, et al.
Publicado: (2026)

Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization
por: Rehmat, Naeem, et al.
Publicado: (2026)

Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
por: Manna, Siladittya, et al.
Publicado: (2024)

Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
por: Ma, Chiyu, et al.
Publicado: (2024)

Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification
por: Gallée, Luisa, et al.
Publicado: (2025)

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
por: Liu, Yang, et al.
Publicado: (2025)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
por: Goswami, Dipam, et al.
Publicado: (2026)

Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
por: Gou, Jiaxiang, et al.
Publicado: (2024)

Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervision
por: Cao, Shuyu, et al.
Publicado: (2025)

Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
por: Jiang, Jerry, et al.
Publicado: (2026)

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
por: Ishmam, Alvi Md, et al.
Publicado: (2024)

HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
por: Liang, Yihao, et al.
Publicado: (2026)

DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation
por: Pan, Qingtao, et al.
Publicado: (2024)

Reliable Cross-modal Alignment via Prototype Iterative Construction
por: Ma, Xiang, et al.
Publicado: (2025)

Dynamic Multimodal Prototype Learning in Vision-Language Models
por: Zhu, Xingyu, et al.
Publicado: (2025)

ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling
por: Jiang, Jianan, et al.
Publicado: (2024)

UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation
por: Thai, Le-Van, et al.
Publicado: (2026)

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
por: Yin, Wenti, et al.
Publicado: (2025)

3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance
por: Xu, Xiaoxu, et al.
Publicado: (2024)

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
por: Li, Yunheng, et al.
Publicado: (2024)

Semantic-Space-Intervened Diffusive Alignment for Visual Classification
por: Li, Zixuan, et al.
Publicado: (2025)

Semi-Supervised Few-Shot Adaptation of Vision-Language Models
por: Silva-Rodríguez, Julio, et al.
Publicado: (2026)

InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
por: Yuan, Muyao, et al.
Publicado: (2025)

Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
por: Ye, Shuchang, et al.
Publicado: (2025)

PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
por: Khandelwal, Anant
Publicado: (2024)

ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification
por: Shi, Kexuan, et al.
Publicado: (2025)

Semantic Alignment of Unimodal Medical Text and Vision Representations
por: Di Folco, Maxime, et al.
Publicado: (2025)

Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling
por: Park, Sungjune, et al.
Publicado: (2025)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
por: Kim, Jiyeong, et al.
Publicado: (2026)

Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification
por: Zhang, Yuqing, et al.
Publicado: (2025)

Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning
por: He, Yushen, et al.
Publicado: (2026)

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
por: de Senneville, Adhemar, et al.
Publicado: (2026)

ERANet: Edge Replacement Augmentation for Semi-Supervised Meniscus Segmentation with Prototype Consistency Alignment and Conditional Self-Training
por: Li, Siyue, et al.
Publicado: (2025)

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
por: Dong, Junhao, et al.
Publicado: (2023)