Copertina

Exploring Weight Balancing on Long-Tailed Recognition Problem

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hasegawa, Naoya, Sato, Issei
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
di: Hasegawa, Naoya, et al.
Pubblicazione: (2024)

Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
di: Kajitsuka, Tokio, et al.
Pubblicazione: (2023)

Can Test-time Computation Mitigate Reproduction Bias in Neural Symbolic Regression?
di: Sato, Shun, et al.
Pubblicazione: (2025)

OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition
di: Chu, Chang, et al.
Pubblicazione: (2026)

End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training
di: Sakamoto, Keitaro, et al.
Pubblicazione: (2024)

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
di: Tomihari, Akiyoshi, et al.
Pubblicazione: (2026)

Benign Overfitting in Token Selection of Attention Mechanism
di: Sakamoto, Keitaro, et al.
Pubblicazione: (2024)

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
di: Sakamoto, Keitaro, et al.
Pubblicazione: (2025)

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
di: Xu, Kevin, et al.
Pubblicazione: (2024)

Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
di: Tomihari, Akiyoshi, et al.
Pubblicazione: (2024)

Top-Down Bayesian Posterior Sampling for Sum-Product Networks
di: Yokoi, Soma, et al.
Pubblicazione: (2024)

Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
di: Koshizuka, Takeshi, et al.
Pubblicazione: (2025)

Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection
di: Fujikawa, Shota, et al.
Pubblicazione: (2026)

To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers
di: Xu, Kevin, et al.
Pubblicazione: (2025)

Rethinking Associative Memory Mechanism in Induction Head
di: Wang, Shuo, et al.
Pubblicazione: (2024)

On the Optimal Memorization Capacity of Transformers
di: Kajitsuka, Tokio, et al.
Pubblicazione: (2024)

Fix Initial Codes and Iteratively Refine Textual Directions Toward Safe Multi-Turn Code Correction
di: Tanaka, Yuto, et al.
Pubblicazione: (2026)

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
di: Xie, Zeke, et al.
Pubblicazione: (2020)

A Formal Comparison Between Chain of Thought and Latent Thought
di: Xu, Kevin, et al.
Pubblicazione: (2025)

Understanding Transformer Optimization via Gradient Heterogeneity
di: Tomihari, Akiyoshi, et al.
Pubblicazione: (2025)

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
di: Zhou, Zi-Hao, et al.
Pubblicazione: (2024)

Long-Tailed Recognition via Information-Preservable Two-Stage Learning
di: Lin, Fudong, et al.
Pubblicazione: (2025)

Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss
di: Lee, Jungi, et al.
Pubblicazione: (2026)

Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
di: Koshizuka, Takeshi, et al.
Pubblicazione: (2023)

On The Relationship Between Continual Learning and Long-Tailed Recognition
di: Molahasani, Mahdiyar, et al.
Pubblicazione: (2023)

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

AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
di: He, Di, et al.
Pubblicazione: (2025)

ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies
di: Katav, Itay, et al.
Pubblicazione: (2025)

BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning
di: Zheng, Hongwei, et al.
Pubblicazione: (2024)

Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
di: Audibert, Alexandre, et al.
Pubblicazione: (2024)

Improving Long-Tailed Object Detection with Balanced Group Softmax and Metric Learning
di: Gaba, Satyam
Pubblicazione: (2025)

Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
di: Tang, Wei, et al.
Pubblicazione: (2025)

Towards Improving Long-Tail Entity Predictions in Temporal Knowledge Graphs through Global Similarity and Weighted Sampling
di: Mirtaheri, Mehrnoosh, et al.
Pubblicazione: (2025)

Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction
di: Zheng, Liangwei Nathan, et al.
Pubblicazione: (2024)

A Survey of Deep Long-Tail Classification Advancements
di: de Alvis, Charika, et al.
Pubblicazione: (2024)

CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
di: Rodriguez, Esther, et al.
Pubblicazione: (2025)

Channel-Free Human Activity Recognition via Inductive-Bias-Aware Fusion Design for Heterogeneous IoT Sensor Environments
di: Hasegawa, Tatsuhito
Pubblicazione: (2026)

A Prefixed Patch Time Series Transformer for Two-Point Boundary Value Problems in Three-Body Problems
di: Hatakeyama, Akira, et al.
Pubblicazione: (2025)

Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning
di: Liu, Lei, et al.
Pubblicazione: (2024)

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM
di: Lyu, Xingyu, et al.
Pubblicazione: (2024)