超越同方差性：面向深度不平衡回归的解耦不确定性优化
Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression
浏览论文内容
中文总结 AI 辅助
针对深度不平衡回归中现有方法忽略异方差性及梯度耦合的问题，提出DUO框架，通过解耦均值-方差优化和分布引导对比学习提升性能，在多基准测试中取得最优结果。
中文摘要 AI 辅助
深度不平衡回归（DIR）广泛存在于年龄估计、深度预测、蛋白质突变活性预测等各类模态的连续预测任务中，标签稀缺的尾部样本通常具有更高的实际价值。然而，大多数现有方法仍基于均方误差或其简单变体学习确定性点映射，隐含假设所有样本的不确定性水平一致，从而忽略了长尾数据中普遍存在的实例级异方差性。我们进一步指出，即使是异方差负对数似然也存在梯度耦合问题，在DIR场景下，该问题会削弱困难尾部样本的学习信号，导致优化惯性及尾部欠拟合。为解决这一问题，我们提出DUO，一种感知不确定性的长尾回归框架。具体而言，该方法将回归目标建模为条件高斯分布，以显式刻画实例级预测不确定性，并通过解耦均值-方差优化将不确定性转换为尾部样本的动态增强信号。此外，我们设计了一种分布引导的对比学习机制，该机制基于样本分布的重叠情况自适应构建正负样本对，从而缓解特征松散及跨标签语义纠缠。在视觉和生物DIR基准测试中，DUO在IMDB-WIKI-DIR、AgeDB-DIR和AAV2-DIR数据集上取得了最优的少-shot bMAE和GM，同时在少-shot MAE上保持竞争力。
英文摘要
Deep Imbalanced Regression (DIR) is pervasive in continuous prediction tasks across diverse modalities, such as age estimation, depth prediction, and protein mutation activity prediction, where label-scarce tail samples often carry higher practical value. However, most existing methods still learn deterministic point mappings under mean squared error or its simple variants, implicitly assuming a uniform uncertainty level across all samples and thereby overlooking the instance-wise heteroscedasticity that is widespread in long-tailed data. We further point out that even heteroscedastic negative log-likelihood suffers from a gradient coupling issue, which, under DIR scenarios, weakens the learning signal of hard tail samples and leads to optimization inertia as well as tail underfitting. To address this, we propose DUO, an uncertainty-aware long-tailed regression framework. Specifically, the proposed method models the regression target as a conditional Gaussian distribution to explicitly characterize instance-level predictive uncertainty, and transforms uncertainty into a dynamic enhancement signal for tail samples through decoupled mean-variance optimization. Furthermore, we design a distribution-guided contrastive learning mechanism that adaptively constructs positive and negative pairs based on the overlap between sample distributions, thereby alleviating feature looseness and cross-label semantic entanglement. Across visual and biological DIR benchmarks, DUO achieves the best few-shot bMAE and GM on IMDB-WIKI-DIR, AgeDB-DIR, and AAV2-DIR while remaining competitive on few-shot MAE.
发表机构
- School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院）
- School of Mathematics and Statistics, Wuhan University（武汉大学数学与统计学院）
- School of Synthetic Biology and Biomanufacturing, Tianjin University（天津大学合成生物学与生物制造学院）
机构由 AI 辅助整理，请以论文原文为准。
