扩展表示多样性：用于视觉定位的调制注意力与重构正则化
Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding
AI总结：
针对指代表达理解模型跨数据集泛化能力有限的问题，提出含mACH与JEPA辅助流的架构及Objects365-Caption数据，实现了强泛化与具竞争力的REC性能。
AI中文摘要：
指代表达理解（REC）通常在特定数据集微调下进行研究，产生的专用模型跨数据集泛化能力有限。本研究从统一开放词汇定位的视角重新审视REC，发现表示退化是扩展单一通用模型的关键障碍。为保留表示多样性，我们提出了一种整体的数据-模型协同设计框架。在架构层面，引入了用于高效令牌级视觉-语言对齐的调制注意力对比头（mACH），以及提供互补梯度支持以保留对齐活跃表示且无推理开销的文本条件JEPA辅助流；在数据层面，引入了Objects365-Caption，为Objects365添加上下文感知的指代表达以用于大规模语言监督。我们进一步提供理论分析表明，互补梯度子空间可保留对齐能力，从而扩展表示多样性。大量实验表明，我们的单检查点框架在标准REC基准上实现了极具竞争力的性能，同时在异构定位数据集上展现出强大的泛化能力，无需针对特定基准进行适配。
英文摘要：
Referring Expression Comprehension (REC) is commonly studied under dataset-specific fine-tuning, resulting in specialist models with limited cross-dataset generalization. In this work, we revisit REC from the perspective of unified open-vocabulary grounding and identify representation degeneration as a key obstacle to scaling a single generalist model. To preserve representation diversity, we propose a holistic data-model co-design framework. Architecturally, we introduce the Modulated Attention-Contrastive Head (mACH) for efficient token-level vision-language alignment and a text-conditioned JEPA auxiliary stream that provides complementary gradient support to preserve alignment-active representations without inference overhead. On the data side, we introduce Objects365-Caption, enriching Objects365 with context-aware referring expressions for large-scale language supervision. We further provide a theoretical analysis showing that complementary gradient subspaces preserve alignment capacity and thereby scale representation diversity. Extensive experiments demonstrate that our single-checkpoint framework achieves highly competitive performance on standard REC benchmarks while exhibiting strong generalization across heterogeneous grounding datasets without benchmark-specific adaptation.
