paper-with-me

Papers

Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View

2026-05-11 · Jinping Wang, Zixin Tong, Zhiwu Xie, Zhiqiang Gao arxiv

Loss reweighting is a widely used strategy for long-tailed classification, but existing reweighting strategies often rely on heuristics and rarely define a well-specified target. Inspired by Neural Collapse (NC), the ideal simplex Equiangular Tight Frame (ETF) terminal geometry suggests equal per-class average loss as a reasonable target for reweighting. Based on the ideal equal loss objective, we consider loss reweighting as an inverse problem and propose an inverse-view reweighting strategy that infers class weights dynamically to match this ideal objective. Empirically, NC metrics suggest our method can effectively reduce the loss imbalance coefficient and closer alignment with NC geometry while consistently outperforming strong long-tailed baselines on different datasets.

📄 PDF Abstract BibTeX arXiv:2605.10047

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation

2020-07-20 · Boris Shirokikh, Alexey Shevtsov, Anvar Kurmukov, Alexandra Dalechina 외

Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-l…

Image SegmentationMedical Image SegmentationSemantic Segmentation

Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks

2026-05-11 · Bum Jun Kim, Gnankan Landry Regis N'guessan arxiv

Physics-informed neural networks (PINNs) train a single neural approximation by minimizing multiple physics- and data-derived losses, but the gradients of these losses often interfere and can stall optimization. Existing…

Instance Awareness of Multi-class Semantic Segmentation Loss Functions

2026-04-27 · Soumya Snigdha Kundu, Florian Kofler, Marina Ivory, Hendrik Moller 외 arxiv

Instance-sensitive losses for semantic segmentation such as blob loss and CC loss were designed to address instance imbalance, ensuring small lesions generate the same gradient as large ones, but operate only on single-c…

Semantic Segmentation

When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study

2024-09-09 · Tomoyuki Obuchi, Toshiyuki Tanaka

A toy model of binary classification is studied with the aim of clarifying the class-wise resampling/reweighting effect on the feature learning performance under the presence of class imbalance. In the analysis, a high-d…

Binary Classificationimbalanced classification

How Sampling Strategy Affects Imbalance Mitigation in LiDAR Segmentation: A Study of Structured vs. Random Point-Based Architectures

2026-08-17 · Antonis Savva, Christos Kyrkou, Theocharis Theocharides arxiv

Class imbalance in LiDAR point clouds poses challenges for semantic segmentation in autonomous navigation and urban mapping. While 2D vision has numerous mitigation techniques, their effectiveness in 3D remains unclear. …

Semantic SegmentationPoint Clouds