Long-tailed Classification from a Bayesian-decision-theory Perspective
Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are largely heuristic and depend heavily on empirical results, lacking theoretical explanation. Furthermore, existing methods overlook the decision loss, which characterizes different costs associated with tailed classes. This paper presents a general and principled framework from a Bayesian-decision-theory perspective, which unifies existing techniques including re-balancing and ensemble methods, and provides theoretical justifications for their effectiveness. From this perspective, we derive a novel objective based on the integrated risk and a Bayesian deep-ensemble approach to improve the accuracy of all classes, especially the "tail". Besides, our framework allows for task-adaptive decision loss which provides provably optimal decisions in varying task scenarios, along with the capability to quantify uncertainty. Finally, We conduct comprehensive experiments, including standard classification, tail-sensitive classification with a new False Head Rate metric, calibration, and ablation studies. Our framework significantly improves the current SOTA even on large-scale real-world datasets like ImageNet.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationSimilar Papers 제목 키워드 기반
Making Reliable and Flexible Decisions in Long-tailed Classification
Long-tailed classification is challenging due to its heavy imbalance in class probabilities. While existing methods often focus on overall accuracy or accuracy for tail classes, they overlook a critical aspect: certain t…
Decision Makingimage-classificationImage ClassificationUncertainty QuantificationTrusted Multi-view Learning for Long-tailed Classification
Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In t…
Decision MakingTowards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i.e., most labels are associated with limited instances. The na\"ive models supervised by such datasets woul…
Data AugmentationLong-tail LearningMultiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studie…
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are long-tailed in nature; it is even impossible when the sample-of-interest co-exists with each other in one co…
Causal InferencecounterfactualCounterfactual ReasoningGeneral Classification+6