Copertina

Can Synthetic Images Serve as Effective and Efficient Class Prototypes?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Dianxing, Fu, Dingjie, Liu, Yuqiao, Wang, Jun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering
di: Liu, Chun, et al.
Pubblicazione: (2025)

EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification
di: Liu, Bingrong, et al.
Pubblicazione: (2025)

Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning
di: Jiang, Shengqin, et al.
Pubblicazione: (2026)

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
di: Moon, WonJun, et al.
Pubblicazione: (2025)

Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
di: Deng, Peihua, et al.
Pubblicazione: (2024)

Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation
di: Zhang, Haixin, et al.
Pubblicazione: (2024)

Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillation
di: Zhu, Shengqian, et al.
Pubblicazione: (2025)

Adaptive Prototype Replay for Class Incremental Semantic Segmentation
di: Zhu, Guilin, et al.
Pubblicazione: (2024)

Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation
di: Zhang, Yumin, et al.
Pubblicazione: (2024)

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
di: Song, Dingjie, et al.
Pubblicazione: (2024)

Insertion Network for Image Sequence Correspondence
di: Su, Dingjie, et al.
Pubblicazione: (2026)

Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport
di: Li, Bin, et al.
Pubblicazione: (2024)

Discriminative Image Generation with Diffusion Models for Zero-Shot Learning
di: Fu, Dingjie, et al.
Pubblicazione: (2024)

What Makes Synthetic Data Effective in Image Segmentation
di: Zhang, Jinjin, et al.
Pubblicazione: (2026)

"You Are Rejected!": An Empirical Study of Large Language Models Taking Hiring Evaluations
di: Fu, Dingjie, et al.
Pubblicazione: (2025)

Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning
di: Kim, Junsu, et al.
Pubblicazione: (2025)

Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation
di: Han, Jiawei, et al.
Pubblicazione: (2024)

PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
di: Guo, Haiyang, et al.
Pubblicazione: (2024)

Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
di: Wang, Hongsong, et al.
Pubblicazione: (2025)

From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
di: Lin, Jinhong, et al.
Pubblicazione: (2024)

HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
di: Shi, Senyuan, et al.
Pubblicazione: (2026)

Effective and Efficient Masked Image Generation Models
di: You, Zebin, et al.
Pubblicazione: (2025)

Optimizing Diffusion Noise Can Serve As Universal Motion Priors
di: Karunratanakul, Korrawe, et al.
Pubblicazione: (2023)

Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
di: Fukuda, Takuma, et al.
Pubblicazione: (2024)

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
di: Wang, Jun, et al.
Pubblicazione: (2024)

Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery
di: Wang, Ye, et al.
Pubblicazione: (2024)

Synthetic Curriculum Reinforces Compositional Text-to-Image Generation
di: Wang, Shijian, et al.
Pubblicazione: (2025)

Few-Shot Object Detection via Spatial-Channel State Space Model
di: Xin, Zhimeng, et al.
Pubblicazione: (2025)

ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning
di: Hou, Wenjin, et al.
Pubblicazione: (2024)

Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces
di: Feng, Yaoxuan, et al.
Pubblicazione: (2026)

Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation
di: Pavan, Martina, et al.
Pubblicazione: (2026)

Anomaly Detection by Effectively Leveraging Synthetic Images
di: Kang, Sungho, et al.
Pubblicazione: (2025)

Improving Text Generation on Images with Synthetic Captions
di: Koh, Jun Young, et al.
Pubblicazione: (2024)

PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification
di: Su, Meijuan, et al.
Pubblicazione: (2023)

Enhanced Prototypical Part Network (EPPNet) For Explainable Image Classification Via Prototypes
di: Atote, Bhushan, et al.
Pubblicazione: (2024)

Federated Active Learning Framework for Efficient Annotation Strategy in Skin-lesion Classification
di: Deng, Zhipeng, et al.
Pubblicazione: (2024)

Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
di: Zhu, Yun, et al.
Pubblicazione: (2025)

Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
di: Qin, Ziheng, et al.
Pubblicazione: (2025)

ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
di: Wu, Jiekai, et al.
Pubblicazione: (2026)

Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
di: Wang, Chong, et al.
Pubblicazione: (2023)