Image de couverture de livre

Reframing Long-Tailed Learning via Loss Landscape Geometry

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Shenghan, Liu, Yiming, Wang, Yanzhen, Wang, Yujia, Lu, Xiankai
Format:	Preprint
Publié:	2026
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

Long-Tail Learning with Rebalanced Contrastive Loss
par: De Alvis, Charika, et autres
Publié: (2023)

Aligned Contrastive Loss for Long-Tailed Recognition
par: Ma, Jiali, et autres
Publié: (2025)

Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss
par: Lu, Wenjun, et autres
Publié: (2025)

VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
par: Peng, Ningkang, et autres
Publié: (2026)

Long-Tailed Visual Recognition via Permutation-Invariant Head-to-Tail Feature Fusion
par: Li, Mengke, et autres
Publié: (2025)

Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification
par: Ma, Yanbiao, et autres
Publié: (2024)

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
par: Zou, Yixiong, et autres
Publié: (2024)

Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations
par: Zhang, Junyi, et autres
Publié: (2026)

Reviving Undersampling for Long-Tailed Learning
par: Yu, Hao, et autres
Publié: (2024)

Invariant Feature Learning for Generalized Long-Tailed Classification
par: Tang, Kaihua, et autres
Publié: (2022)

3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation
par: Pan, Feiyu, et autres
Publié: (2024)

Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
par: Li, Mengke, et autres
Publié: (2023)

Learning from Neighbors: Category Extrapolation for Long-Tail Learning
par: Zhao, Shizhen, et autres
Publié: (2024)

CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
par: Li, Mengke, et autres
Publié: (2026)

Tail-Aware Post-Training Quantization for 3D Geometry Models
par: Pan, Sicheng, et autres
Publié: (2026)

SEAL: Semantic Attention Learning for Long Video Representation
par: Wang, Lan, et autres
Publié: (2024)

Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
par: Yang, Jinye, et autres
Publié: (2023)

Decoupled Contrastive Learning for Long-Tailed Recognition
par: Xuan, Shiyu, et autres
Publié: (2024)

MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
par: Cui, Feng-Qi, et autres
Publié: (2025)

Revisiting Adversarial Training under Long-Tailed Distributions
par: Yue, Xinli, et autres
Publié: (2024)

Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
par: Du, Chaoqun, et autres
Publié: (2024)

Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
par: Pan, Feiyu, et autres
Publié: (2024)

AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction
par: Rao, Bin, et autres
Publié: (2025)

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
par: Fang, Shiyu, et autres
Publié: (2025)

Long-Tailed Continual Learning For Visual Food Recognition
par: He, Jiangpeng, et autres
Publié: (2023)

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
par: Wagner, Royden, et autres
Publié: (2026)

GGPT: Geometry Grounded Point Transformer
par: Chen, Yutong, et autres
Publié: (2026)

Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
par: He, Yina, et autres
Publié: (2024)

Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
par: Feng, Shuai, et autres
Publié: (2025)

The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
par: Chopra, Shivang, et autres
Publié: (2026)

A Conditional Probability Framework for Compositional Zero-shot Learning
par: Wu, Peng, et autres
Publié: (2025)

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

Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation
par: Pang, Zhanzhong, et autres
Publié: (2025)

NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition
par: Tan, Zichang, et autres
Publié: (2023)

CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning
par: Zhang, Ruichi, et autres
Publié: (2026)

TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning
par: Li, Linjie, et autres
Publié: (2024)

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
par: Peng, Ningkang, et autres
Publié: (2026)

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification
par: Yan, Jiexuan, et autres
Publié: (2024)

Rectify the Regression Bias in Long-Tailed Object Detection
par: Zhu, Ke, et autres
Publié: (2024)

Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation
par: Wijenayake, Buddhi, et autres
Publié: (2026)