Copertina

Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Han, Boyu, Xu, Qianqian, Bao, Shilong, Yang, Zhiyong, Cui, Ruochen, Zhao, Xilin, Huang, Qingming
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
di: Han, Boyu, et al.
Pubblicazione: (2026)

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
di: Han, Boyu, et al.
Pubblicazione: (2025)

Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation
di: Li, Feiran, et al.
Pubblicazione: (2025)

Dual-Stage Reweighted MoE for Long-Tailed Egocentric Mistake Detection
di: Han, Boyu, et al.
Pubblicazione: (2025)

BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
di: Li, Feiran, et al.
Pubblicazione: (2026)

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification
di: Lu, Zhiguang, et al.
Pubblicazione: (2024)

Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
di: Bao, Shilong, et al.
Pubblicazione: (2025)

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
di: Han, Boyu, et al.
Pubblicazione: (2024)

ReconBoost: Boosting Can Achieve Modality Reconcilement
di: Hua, Cong, et al.
Pubblicazione: (2024)

One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
di: Li, Feiran, et al.
Pubblicazione: (2025)

From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
di: Liu, Yang, et al.
Pubblicazione: (2026)

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection
di: Li, Feiran, et al.
Pubblicazione: (2024)

Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations
di: Jiang, Yangbangyan, et al.
Pubblicazione: (2025)

Self-supervised Representation Learning with Local Aggregation for Image-based Profiling
di: Dai, Siran, et al.
Pubblicazione: (2025)

Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
di: Liu, Yang, et al.
Pubblicazione: (2025)

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
di: Meng, Benyuan, et al.
Pubblicazione: (2024)

Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
di: Pei, Gaozheng, et al.
Pubblicazione: (2025)

Exploring Structural Degradation in Dense Representations for Self-supervised Learning
di: Dai, Siran, et al.
Pubblicazione: (2025)

When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
di: Liu, Yang, et al.
Pubblicazione: (2025)

Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
di: Xu, Ganxi, et al.
Pubblicazione: (2025)

Regularized Contrastive Partial Multi-view Outlier Detection
di: Wang, Yijia, et al.
Pubblicazione: (2024)

Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
di: Xu, Zhikang, et al.
Pubblicazione: (2026)

HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models
di: Lu, Zhiguang, et al.
Pubblicazione: (2025)

Semantic Concentration for Self-Supervised Dense Representations Learning
di: Wen, Peisong, et al.
Pubblicazione: (2025)

Making Training-Free Diffusion Segmentors Scale with the Generative Power
di: Meng, Benyuan, et al.
Pubblicazione: (2026)

Guiding Diffusion Models with Semantically Degraded Conditions
di: Han, Shilong, et al.
Pubblicazione: (2026)

DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Vartiations
di: Yang, Zhiyong, et al.
Pubblicazione: (2024)

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
di: Meng, Benyuan, et al.
Pubblicazione: (2024)

Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
di: Pei, Gaozheng, et al.
Pubblicazione: (2025)

Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
di: Wang, Zitai, et al.
Pubblicazione: (2024)

Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning
di: Tu, Yunbin, et al.
Pubblicazione: (2024)

Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval
di: Liu, Yang, et al.
Pubblicazione: (2024)

A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
di: Wang, Zitai, et al.
Pubblicazione: (2023)

Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection
di: Yu, Zhipeng, et al.
Pubblicazione: (2025)

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model
di: Wang, Yu, et al.
Pubblicazione: (2026)

Patch-based Representation and Learning for Efficient Deformation Modeling
di: Chen, Ruochen, et al.
Pubblicazione: (2026)

PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models
di: Li, Pengbo, et al.
Pubblicazione: (2025)

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation
di: Xiang, Wenzhao, et al.
Pubblicazione: (2025)

A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement
di: Pei, Gaozheng, et al.
Pubblicazione: (2025)

VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
di: Tang, Jimin, et al.
Pubblicazione: (2026)