Image de couverture de livre

Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Zikun, Sun, Yushuai, Pei, Wenjie, Li, Xin, Wang, Yaowei
Format:	Preprint
Publié:	2025
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

Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
par: Sun, Yushuai, et autres
Publié: (2025)

MixBCT: Towards Self-Adapting Backward-Compatible Training
par: Liang, Yu, et autres
Publié: (2023)

Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation
par: Zhou, Zikun, et autres
Publié: (2024)

RTracker: Recoverable Tracking via PN Tree Structured Memory
par: Huang, Yuqing, et autres
Publié: (2024)

Deeply-Conditioned Image Compression via Self-Generated Priors
par: Zhao, Zhineng, et autres
Publié: (2025)

Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
par: Ning, Zhenhua, et autres
Publié: (2026)

Lifelong Person Re-Identification with Backward-Compatibility
par: Oh, Minyoung, et autres
Publié: (2024)

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
par: Ricci, Simone, et autres
Publié: (2024)

Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detection
par: Zhou, Ziqing, et autres
Publié: (2025)

Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems
par: Wang, Xinyu, et autres
Publié: (2025)

Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
par: Chen, Yang, et autres
Publié: (2025)

JPEG Processing Neural Operator for Backward-Compatible Coding
par: Han, Woo Kyoung, et autres
Publié: (2025)

A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
par: Zhang, Jinghua, et autres
Publié: (2023)

ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking
par: Chen, Jianqiu, et autres
Publié: (2025)

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model
par: Zhou, Li, et autres
Publié: (2024)

Motion-aware Latent Diffusion Models for Video Frame Interpolation
par: Huang, Zhilin, et autres
Publié: (2024)

Relax DARTS: Relaxing the Constraints of Differentiable Architecture Search for Eye Movement Recognition
par: Zhu, Hongyu, et autres
Publié: (2024)

Pairwise Alignment & Compatibility for Arbitrarily Irregular Image Fragments
par: Shahar, Ofir Itzhak, et autres
Publié: (2025)

k-fold Subsampling based Sequential Backward Feature Elimination
par: Park, Jeonghwan, et autres
Publié: (2025)

Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment
par: Zhou, Kai, et autres
Publié: (2025)

Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
par: Li, Deng, et autres
Publié: (2024)

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
par: Jiang, Zhiying, et autres
Publié: (2024)

RadioDUN: A Physics-Inspired Deep Unfolding Network for Radio Map Estimation
par: Chen, Taiqin, et autres
Publié: (2025)

Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
par: Zhang, Yuhang, et autres
Publié: (2025)

Closing the Alignment-Maturity Gap in Federated Prototype Learning
par: Casado-Diez, Mario, et autres
Publié: (2026)

Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
par: Zang, Zehua, et autres
Publié: (2026)

Prototype Learning for Micro-gesture Classification
par: Chen, Guoliang, et autres
Publié: (2024)

Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
par: Chen, Yanjun, et autres
Publié: (2025)

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
par: Jung, Jaewoo, et autres
Publié: (2024)

Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
par: Li, Zhiyong, et autres
Publié: (2026)

EPL: Empirical Prototype Learning for Deep Face Recognition
par: Fan, Weijia, et autres
Publié: (2024)

Dynamic Multimodal Prototype Learning in Vision-Language Models
par: Zhu, Xingyu, et autres
Publié: (2025)

Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
par: Wang, Fuyun, et autres
Publié: (2025)

MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking
par: Liu, Xinqi, et autres
Publié: (2024)

PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification
par: Su, Meijuan, et autres
Publié: (2023)

Reliable Cross-modal Alignment via Prototype Iterative Construction
par: Ma, Xiang, et autres
Publié: (2025)

Prototype-Aware Multimodal Alignment for Open-Vocabulary Visual Grounding
par: Xie, Jiangnan, et autres
Publié: (2025)

RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
par: Wen, Junwei, et autres
Publié: (2026)

DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment
par: Han, Jianhong, et autres
Publié: (2024)

Conditional Prototype Rectification Prompt Learning
par: Chen, Haoxing, et autres
Publié: (2024)