arXiv cs.AI· Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Qingming Huang·· 4 小时前AI 评分26
AUC 遇上生成式重建:面向平衡视觉表征学习的统一原则
When AUC Meets Generative Reconstruction: A Unified Principle for Balanced Visual Representation Learning
AI 导读
研究提出 AUC Generative Reconstruction(AUCGR)与 Partial AUC Generative Reconstruction(pAUCGR),将生成式重建重构为生成输出流形内的判别排序问题,通过让匹配样本对的得分高于不匹配样本对来优化 AUC,避免复合损失函数带来的梯度干扰与优化冲突。
正文 · 原文
Abstract:Multimodal large language models (MLLMs) require visual encoders that extract fine-grained visual features while constructing semantically disentangled and discriminative representations. Conventional methodologies encounter a fundamental trade-off: contrastive learning enhances inter-class discrimination by suppressing intra-class variability, whereas generative reconstruction emphasizes perceptual fidelity but lacks explicit comparative supervision. The naive aggregation of these objectives via composite loss functions often induces optimization conflicts and instability due to gradient interference within the shared latent space. To resolve this, we introduce a unified representation-learning paradigm that reformulates generative reconstruction as a discriminative ranking problem within the generative output manifold. Our approach maintains perceptual reconstruction as a supervisory signal and integrates a ranking-based discriminative constraint by systematically ordering matched and mismatched reconstruction outputs. This formulation embeds discriminative information seamlessly into the generative process, alleviating the risk of loss competition. Specifically, we propose AUC Generative Reconstruction (AUCGR), which optimizes the area under the ROC curve (AUC) by ensuring higher scores for matched pairs than for mismatched pairs, and Partial AUC Generative Reconstruction (pAUCGR), which addresses supervision bias by focusing on mismatched comparisons within reliable feature subspaces. The proposed objectives are designed to be plug-and-play, requiring no architectural modifications to existing generative reconstruction frameworks. Theoretical analysis establishes rigorous connections to AUC/pAUC optimization and provides generalization guarantees. Extensive experiments validate that our method advances both discriminative accuracy and fine-grained perceptual representation.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.22094 [cs.CV] |
| (or arXiv:2611.22094v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22094 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Boyu Han [view email]
[v1]
Tue, 17 Nov 2026 02:24:09 UTC (9,775 KB)
来源:arXiv cs.AI · arxiv.org