Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
This work addresses the need for more flexible and robust low-shot classification methods in computer vision, though it is incremental as it builds on existing CLIP and ensemble techniques.
The paper tackles the problem of low-shot image classification by proposing a probabilistic ensemble framework that integrates CLIP with other pre-trained models using Gaussian processes, resulting in consistent outperformance over competitive baselines in predictive performance and improved uncertainty quantification.
Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based methods lack the flexibility to effectively incorporate other pre-trained models that encompass knowledge distinct from CLIP. To bridge the gap, this work proposes a simple and effective probabilistic model ensemble framework based on Gaussian processes, which have previously demonstrated remarkable efficacy in processing small data. We achieve the integration of prior knowledge by specifying the mean function with CLIP and the kernel function with an ensemble of deep kernels built upon various pre-trained models. By regressing the classification label directly, our framework enables analytical inference, straightforward uncertainty quantification, and principled hyper-parameter tuning. Through extensive experiments on standard benchmarks, we demonstrate that our method consistently outperforms competitive ensemble baselines regarding predictive performance. Additionally, we assess the robustness of our method and the quality of the yielded uncertainty estimates on out-of-distribution datasets. We also illustrate that our method, despite relying on label regression, still enjoys superior model calibration compared to most deterministic baselines.