Copertina

Reducing Class-Wise Performance Disparity via Margin Regularization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Beier, Zhao, Kesen, Cui, Jiequan, Sun, Qianru, Zhou, Yuan, Yang, Xun, Zhang, Hanwang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization
di: Zhao, Kesen, et al.
Pubblicazione: (2025)

Robust Fine-tuning of Zero-shot Models via Variance Reduction
di: Zhu, Beier, et al.
Pubblicazione: (2024)

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness
di: Cui, Jiequan, et al.
Pubblicazione: (2024)

Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness
di: Zhu, Beier, et al.
Pubblicazione: (2025)

Real-Time Motion-Controllable Autoregressive Video Diffusion
di: Zhao, Kesen, et al.
Pubblicazione: (2025)

Enhancing CLIP Robustness via Cross-Modality Alignment
di: Zhu, Xingyu, et al.
Pubblicazione: (2025)

Hierarchical Semantic Alignment for Image Clustering
di: Zhu, Xingyu, et al.
Pubblicazione: (2025)

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
di: Zhu, Beier, et al.
Pubblicazione: (2023)

Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought
di: Zhao, Kesen, et al.
Pubblicazione: (2026)

Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!
di: Zhou, Junbao, et al.
Pubblicazione: (2025)

Generative Distribution Distillation
di: Cui, Jiequan, et al.
Pubblicazione: (2025)

Generalized Kullback-Leibler Divergence Loss
di: Cui, Jiequan, et al.
Pubblicazione: (2025)

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
di: Zhu, Xingyu, et al.
Pubblicazione: (2026)

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
di: Zhu, Xingyu, et al.
Pubblicazione: (2026)

Decoupled Kullback-Leibler Divergence Loss
di: Cui, Jiequan, et al.
Pubblicazione: (2023)

CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction
di: Zhou, Yuan, et al.
Pubblicazione: (2024)

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
di: Zhu, Beier, et al.
Pubblicazione: (2023)

Parallel Diffusion Solver via Residual Dirichlet Policy Optimization
di: Wang, Ruoyu, et al.
Pubblicazione: (2025)

Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
di: Qi, Jiaxin, et al.
Pubblicazione: (2022)

Pushing Rendering Boundaries: Hard Gaussian Splatting
di: Xu, Qingshan, et al.
Pubblicazione: (2024)

Instruction Tuning-free Visual Token Complement for Multimodal LLMs
di: Wang, Dongsheng, et al.
Pubblicazione: (2024)

Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization
di: Liu, Duo, et al.
Pubblicazione: (2025)

Doubly Abductive Counterfactual Inference for Text-based Image Editing
di: Song, Xue, et al.
Pubblicazione: (2024)

Few-shot Learner Parameterization by Diffusion Time-steps
di: Yue, Zhongqi, et al.
Pubblicazione: (2024)

DragNeXt: Rethinking Drag-Based Image Editing
di: Zhou, Yuan, et al.
Pubblicazione: (2025)

Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models
di: Zhu, Beier, et al.
Pubblicazione: (2025)

NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos
di: Xu, Qingshan, et al.
Pubblicazione: (2025)

Aligned Contrastive Loss for Long-Tailed Recognition
di: Ma, Jiali, et al.
Pubblicazione: (2025)

3D Question Answering via only 2D Vision-Language Models
di: Wang, Fengyun, et al.
Pubblicazione: (2025)

LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
di: Song, Xue, et al.
Pubblicazione: (2024)

Narrowing Class-Wise Robustness Gaps in Adversarial Training
di: Amerehi, Fatemeh, et al.
Pubblicazione: (2025)

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
di: Pan, Linchao, et al.
Pubblicazione: (2025)

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning
di: Zhu, Xingyu, et al.
Pubblicazione: (2026)

MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering
di: Zhou, Yuan, et al.
Pubblicazione: (2026)

Prompt-aligned Gradient for Prompt Tuning
di: Zhu, Beier, et al.
Pubblicazione: (2022)

Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
di: Zhu, Xingyu, et al.
Pubblicazione: (2024)

Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
di: Wu, Zike, et al.
Pubblicazione: (2024)

Generalized Visual Relation Detection with Diffusion Models
di: Gao, Kaifeng, et al.
Pubblicazione: (2025)

Region-Wise Correspondence Prediction between Manga Line Art Images
di: Li, Yingxuan, et al.
Pubblicazione: (2025)

Free Lunch for Stabilizing Rectified Flow Inversion
di: Wang, Chenru, et al.
Pubblicazione: (2026)