小模型也能高效推理：用内部特征增强视觉语言模型性能
Efficient Test-Time Scaling for Small Vision-Language Models
- 利用模型内特征生成多视角输入，无参数更新聚合输出
- 在9个基准上提升性能，计算开销仍适合资源受限场景
- 无需额外调参，适配不同规模和架构的小型视觉语言模型
小型视觉语言模型（VLMs）在计算效率上优于大模型，但泛化能力与下游任务表现较弱。现有测试时扩展技术虽可缓解此问题，但通常计算开销大，违背小型模型的轻量设计初衷。为此，我们提出两种新颖且高效的测试时扩展策略，均基于模型内部特征而非外部监督：(i) 测试时增强（TTAug），通过生成多个增强输入，在不更新参数的情况下以标记级聚合输出；(ii) 测试时自适应（TTAdapt），利用TTAug生成的一致性伪标签，在推理过程中调整模型参数。在九个基准上的广泛实验表明，该方法在保持计算效率的同时实现稳定性能提升，且适用于不同规模的模型及多种VLM结构，无需额外调优。
原文摘要 · Abstract (English)
Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling techniques, but existing methods are typically computationally demanding, contradicting the resource-efficient design goals of small models. To address these limitations, we propose two novel and efficient test-time scaling strategies that leverage the model-internal features rather than external supervision: (i) Test-Time Augmentation (TTAug), which generates multiple augmented inputs and aggregates outputs at the token level without parameter updates, and (ii) Test-Time Adaptation (TTAdapt), which adapts model parameters during inference using consensus-based pseudolabels from TTAug. Through extensive experiments across nine benchmarks, we demonstrate consistent performance improvements while maintaining computational efficiency suitable for resource-constrained environments. The generality of our approach is demonstrated both within models at different scales and across different VLMs without additional tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。