Efficient Test-Time Scaling for Small Vision-Language Models
This work addresses performance limitations in small vision-language models for resource-constrained applications, representing an incremental improvement over existing test-time methods.
The paper tackled the problem of weak generalization and performance in small vision-language models by proposing two efficient test-time scaling strategies, TTAug and TTAdapt, which improved performance across nine benchmarks while maintaining computational efficiency suitable for resource-constrained environments.
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.