Image de couverture de livre

UNIC: Universal Classification Models via Multi-teacher Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sariyildiz, Mert Bulent, Weinzaepfel, Philippe, Lucas, Thomas, Larlus, Diane, Kalantidis, Yannis
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
par: Sariyildiz, Mert Bulent, et autres
Publié: (2025)

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
par: Kalantidis, Yannis, et autres
Publié: (2024)

Task Alignment: A simple and effective proxy for model merging in computer vision
par: de Jorge, Pau, et autres
Publié: (2026)

Kinaema: a recurrent sequence model for memory and pose in motion
par: Sariyildiz, Mert Bulent, et autres
Publié: (2025)

Label Propagation for Zero-shot Classification with Vision-Language Models
par: Stojnić, Vladan, et autres
Publié: (2024)

On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
par: Marrie, Juliette, et autres
Publié: (2024)

Win-Win: Training High-Resolution Vision Transformers from Two Windows
par: Leroy, Vincent, et autres
Publié: (2023)

UNIC: Unified In-Context Video Editing
par: Ye, Zixuan, et autres
Publié: (2025)

ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
par: Suma, Pavel, et autres
Publié: (2026)

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
par: Baradel, Fabien, et autres
Publié: (2024)

CondiMen: Conditional Multi-Person Mesh Recovery
par: Romain, Brégier, et autres
Publié: (2024)

LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
par: Stojnić, Vladan, et autres
Publié: (2025)

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
par: Tschernezki, Vadim, et autres
Publié: (2025)

PoseScript: Linking 3D Human Poses and Natural Language
par: Delmas, Ginger, et autres
Publié: (2022)

What could go wrong? Discovering and describing failure modes in computer vision
par: Csurka, Gabriela, et autres
Publié: (2024)

What does really matter in image goal navigation?
par: Monaci, Gianluca, et autres
Publié: (2025)

Purposer: Putting Human Motion Generation in Context
par: Ugrinovic, Nicolas, et autres
Publié: (2024)

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes
par: Marrie, Juliette, et autres
Publié: (2024)

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
par: Jiang, Zeren, et autres
Publié: (2026)

UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation
par: Zhao, Chengfeng, et autres
Publié: (2026)

Human Mesh Modeling for Anny Body
par: Brégier, Romain, et autres
Publié: (2025)

UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation
par: Duan, Lunhao, et autres
Publié: (2024)

UNIC: Learning Unified Multimodal Extrinsic Contact Estimation
par: Xu, Zhengtong, et autres
Publié: (2026)

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
par: Rojas, Sara, et autres
Publié: (2025)

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation
par: Delmas, Ginger, et autres
Publié: (2024)

PoseFix: Correcting 3D Human Poses with Natural Language
par: Delmas, Ginger, et autres
Publié: (2023)

Cross-view and Cross-pose Completion for 3D Human Understanding
par: Armando, Matthieu, et autres
Publié: (2023)

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
par: Jang, Wonbong, et autres
Publié: (2025)

AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
par: Li, Yuqi, et autres
Publié: (2025)

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
par: Jiang, Zeren, et autres
Publié: (2025)

MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion
par: Duisterhof, Bardienus, et autres
Publié: (2024)

EPIC Fields: Marrying 3D Geometry and Video Understanding
par: Tschernezki, Vadim, et autres
Publié: (2023)

Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
par: Liu, Peng
Publié: (2021)

Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
par: Yu, Zeqin, et autres
Publié: (2025)

DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models
par: Algan, Furkan Mert, et autres
Publié: (2026)

GDA-YOLO11: Amodal Instance Segmentation for Occlusion-Robust Robotic Fruit Harvesting
par: Beldek, Caner, et autres
Publié: (2026)

Multi-vision-based Picking Point Localisation of Target Fruit for Harvesting Robots
par: Beldek, C., et autres
Publié: (2025)

PANDAS: Prototype-based Novel Class Discovery and Detection
par: Hayes, Tyler L., et autres
Publié: (2024)

MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and Classification
par: Yang, Zijiang, et autres
Publié: (2025)

Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique
par: Zheng, Qiang, et autres
Publié: (2024)