paper-with-me

Papers

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

2024-12-20 · Minseok Son, Inyong Koo, Jinyoung Park, Changick Kim

When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known sample distributions, primarily addressing different classification difficulties at the class level. However, these approaches often overlook the instance difficulty variation within each class. In this paper, we propose a difficulty-aware balancing margin (DBM) loss, which considers both class imbalance and instance difficulty. DBM loss comprises two components: a class-wise margin to mitigate learning bias caused by imbalanced class frequencies, and an instance-wise margin assigned to hard positive samples based on their individual difficulty. DBM loss improves class discriminativity by assigning larger margins to more difficult samples. Our method seamlessly combines with existing approaches and consistently improves performance across various long-tailed recognition benchmarks.

📄 PDF Abstract BibTeX arXiv:2412.15477

Code (1)

quotation2520/dbm_ltr 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Small-Margin Preferences Still Matter-If You Train Them Right

2026-02-01 · Jinlong Pang, Zhaowei Zhu, Na Di, Yichi Zhang 외 arxiv

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heurist…

Dual-Balancing for Physics-Informed Neural Networks

2025-05-16 · Chenhong Zhou, Jie Chen, Zaifeng Yang, Ching Eng Png

Physics-informed neural networks (PINNs) have emerged as a new learning paradigm for solving partial differential equations (PDEs) by enforcing the constraints of physical equations, boundary conditions (BCs), and initia…

Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate Prediction

2026-05-24 · Moyu Zhang, Yun Chen, Yujun Jin, Jinxin Hu 외 arxiv

Generative pre-training via discrete diffusion provides dense reconstruction supervision across all feature fields simultaneously, mitigating representation collapse from data sparsity in CTR prediction. However, all exi…

Click-Through Rate Prediction

DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification

2023-10-18 · Yuanyuan Wang, Yang Zhang, Zhiyong Wu, Zhihan Yang 외

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming an…

Data AugmentationDiversitySpeaker Verification

Gradient-Aware Logit Adjustment Loss for Long-tailed Classifier

2024-03-14 · Fan Zhang, Wei Qin, Weijieying Ren, Lei Wang 외

In the real-world setting, data often follows a long-tailed distribution, where head classes contain significantly more training samples than tail classes. Consequently, models trained on such data tend to be biased towa…