Imagen de Portada

Reframing Long-Tailed Learning via Loss Landscape Geometry

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Shenghan, Liu, Yiming, Wang, Yanzhen, Wang, Yujia, Lu, Xiankai
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Long-Tail Learning with Rebalanced Contrastive Loss
por: De Alvis, Charika, et al.
Publicado: (2023)

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

Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss
por: Lu, Wenjun, et al.
Publicado: (2025)

VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
por: Peng, Ningkang, et al.
Publicado: (2026)

Long-Tailed Visual Recognition via Permutation-Invariant Head-to-Tail Feature Fusion
por: Li, Mengke, et al.
Publicado: (2025)

Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification
por: Ma, Yanbiao, et al.
Publicado: (2024)

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
por: Zou, Yixiong, et al.
Publicado: (2024)

Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations
por: Zhang, Junyi, et al.
Publicado: (2026)

Reviving Undersampling for Long-Tailed Learning
por: Yu, Hao, et al.
Publicado: (2024)

Invariant Feature Learning for Generalized Long-Tailed Classification
por: Tang, Kaihua, et al.
Publicado: (2022)

3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation
por: Pan, Feiyu, et al.
Publicado: (2024)

Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
por: Li, Mengke, et al.
Publicado: (2023)

Learning from Neighbors: Category Extrapolation for Long-Tail Learning
por: Zhao, Shizhen, et al.
Publicado: (2024)

CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
por: Li, Mengke, et al.
Publicado: (2026)

Tail-Aware Post-Training Quantization for 3D Geometry Models
por: Pan, Sicheng, et al.
Publicado: (2026)

SEAL: Semantic Attention Learning for Long Video Representation
por: Wang, Lan, et al.
Publicado: (2024)

Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
por: Yang, Jinye, et al.
Publicado: (2023)

Decoupled Contrastive Learning for Long-Tailed Recognition
por: Xuan, Shiyu, et al.
Publicado: (2024)

MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
por: Cui, Feng-Qi, et al.
Publicado: (2025)

Revisiting Adversarial Training under Long-Tailed Distributions
por: Yue, Xinli, et al.
Publicado: (2024)

Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
por: Du, Chaoqun, et al.
Publicado: (2024)

Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
por: Pan, Feiyu, et al.
Publicado: (2024)

AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction
por: Rao, Bin, et al.
Publicado: (2025)

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
por: Fang, Shiyu, et al.
Publicado: (2025)

Long-Tailed Continual Learning For Visual Food Recognition
por: He, Jiangpeng, et al.
Publicado: (2023)

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
por: Wagner, Royden, et al.
Publicado: (2026)

GGPT: Geometry Grounded Point Transformer
por: Chen, Yutong, et al.
Publicado: (2026)

Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
por: He, Yina, et al.
Publicado: (2024)

Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
por: Feng, Shuai, et al.
Publicado: (2025)

The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
por: Chopra, Shivang, et al.
Publicado: (2026)

A Conditional Probability Framework for Compositional Zero-shot Learning
por: Wu, Peng, et al.
Publicado: (2025)

The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation
por: Fang, Hao, et al.
Publicado: (2025)

Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation
por: Pang, Zhanzhong, et al.
Publicado: (2025)

NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition
por: Tan, Zichang, et al.
Publicado: (2023)

CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning
por: Zhang, Ruichi, et al.
Publicado: (2026)

TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning
por: Li, Linjie, et al.
Publicado: (2024)

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
por: Peng, Ningkang, et al.
Publicado: (2026)

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification
por: Yan, Jiexuan, et al.
Publicado: (2024)

Rectify the Regression Bias in Long-Tailed Object Detection
por: Zhu, Ke, et al.
Publicado: (2024)

Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation
por: Wijenayake, Buddhi, et al.
Publicado: (2026)