CORTEXA
← Browse
arxivcs.LGcs.CV2026-07-24

Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition

Yi-Hang Zhu, Rajeev Raman, Shiqi Su, Jianyuan Sun, Xinyu Yang, Nan Xing, Huiyu Zhou

Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks. However, their performance degrades significantly on imbalanced datasets. Although Balanced Softmax is widely adopted as a state-of-the-art rebalancing method, it possesses inherent limitations, such as yielding disproportionately lower testing accuracy for tail classes. To mitigate these shortcomings, we propose the Class-Balanced Softmax (CBS). Rooted in a theoretical Bayesian framework and a heuristic power-law assumption, the CBS is a simple logit adjustment that is computationally inexpensive and easily integrated into existing pipelines. Furthermore, we characterise a fundamental phenomenon in models trained on imbalanced data, termed the preference issue, wherein models exhibit higher training error and a larger generalisation gap for classes with limited data. To quantify this issue, we introduce a novel metric and demonstrate that CBS effectively mitigates the preference issue. Extensive experiments on large-scale benchmarks show that CBS is highly scalable and outperforms existing methods, including Balanced Softmax.

View free PDFSource page

Related papers

arxivcs.LGcs.CV2026-07-04

Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification

Ha-Hieu Pham, Hai-Dang Nguyen, Dang P. M. Cao, Thanh-Huy Nguyen, Min Xu, Trung-Nghia Le, et al.

In chest X-ray (CXR) classification, acceptable ranking performance can still leave rare-positive patients below threshold, especially within subgroups. We study this pre-deployment fairness problem as an audit question: after a long-tailed multi-label CXR model is converted from…

View free PDFSource page
arxivcs.LGcs.CV2026-07-10

A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition

Juan Terven, Diana Margarita Córdova Esparza, Julio Alejandro Romero Gonzalez, Edgar Arturo Chávez Urbiola, Francisco Javier Willars Rodriguez, Juan Bautista Hurtado Ramos, et al.

Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes. We ask whether, after Balanced Softmax training, the remaining tail error can be reduced by retraining only the classifier. We evaluate BS-cRT, a two-stag…

View free PDFSource page
arxivcs.CVcs.LG2026-07-06

Taxlifier: Leveraging Disease Taxonomy for Enhanced Multi-Label Classification in Chest Radiography

Mohammad S. Majdi, Jeffrey J. Rodriguez

Accurate and efficient classification of thoracic diseases in chest X-ray (CXR) images is crucial for timely diagnosis and treatment. However, the presence of multiple pathologies with overlapping visual characteristics poses significant challenges for automated classification sy…

View free PDFSource page
arxivcs.CVcs.LG2026-07-17

Hierarchical Specialised Ensembles for Classification of Zebrafish Phenotypes Using the Selected Image Recognition Methods

Piotr S. Maciąg, Monika Maciąg, Magdalena Majdan

We propose and evaluate three hierarchical ensemble setups for zebrafish phenotype classification from embryo images. In all setups, stage 1 uses a single four-class classifier to assign images to one of the exclusive phenotypes: Normal, Chorion, Dead, or Other. Images classified…

View free PDFSource page
arxivcs.ROcs.AIcs.CVcs.LG2026-06-29

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li, Jianwei Gong

Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization…

View free PDFSource page
arxivcs.LGcs.CVeess.IV2026-07-08

Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection

Joao Pinelo, Joao Goncalves, Arun Shukla, Adriana Santos-Ferreira

The Internal Waves Service screens the Sentinel-1 Wave-mode archive for internal solitary waves, routing detections to experts whose adjudication time is the resource the effort exists to conserve. Because attention is the cost of error, precision leads. Its classifier was traine…

View free PDFSource page