论文

AUCGR:将生成式重构转化为判别式排序的视觉表征学习新范式

When AUC Meets Generative Reconstruction: A Unified Principle for Balanced Visual Representation Learning

精选理由

做 MLLM 视觉编码的人该看看这篇。它把重建损失改成 AUC 排序问题,即插即用不用改架构,避免了对比学习和重建联合训练时的梯度打架,论文还给了泛化性证明。

arXiv 论文提出 AUC Generative Reconstruction(AUCGR)与 Partial AUC 变体(pAUCGR)两种目标函数,用于解决多模态大语言模型(MLLM)视觉编码器中对比学习与生成重构之间的目标冲突。

正文

核心思路是把生成重构重新表述为生成输出流形上的判别式排序问题:通过 AUC 优化保证匹配对的重建得分高于不匹配对,从而在不引入损失竞争的前提下嵌入判别信息。pAUCGR 进一步聚焦可靠特征子空间内的不匹配比较,缓解监督偏差。

两种目标是即插即用的,不需要修改现有生成重构框架的架构。论文给出了与 AUC/pAUC 优化相关的理论分析和泛化保证,实验验证了方法在判别精度与细粒度感知表征上的同步提升。

原文 · arXiv cs.LG

When AUC Meets Generative Reconstruction: A Unified Principle for Balanced Visual Representation Learning

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.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:AUCGR、MLLM、视觉编码器、表征学习,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Qingming Huang),经 AITOP 多维评分管线结构化提炼。