# Low-Resource Vision Challenges for Foundation Models Source: [Low-Resource Vision Challenges for Foundation Models]() Collection index: [llms.txt]() Data updated: 2026-01-02T05:42:09.269Z Authors: Yunhua Zhang, Hazel Doughty, Cees G.M. Snoek Published: 2024-01-09T18:40:52.000Z ## Abstract Low-resource settings are well-established in natural language processing, where many languages lack sufficient data for deep learning at scale. However, low-resource problems are under-explored in computer vision. In this paper, we address this gap and explore the challenges of low-resource image tasks with vision foundation models. We first collect a benchmark of genuinely low-resource image data, covering historic maps, circuit diagrams, and mechanical drawings. These low-resource settings all share three challenges: data scarcity, fine-grained differences, and the distribution shift from natural images to the specialized domain of interest. While existing foundation models have shown impressive generalizability, we find they cannot transfer well to our low-resource tasks. To begin to tackle the challenges of low-resource vision, we introduce one simple baseline per challenge. Specifically, we i) enlarge the data space by generative models, ii) adopt the best sub-kernels to encode local regions for fine-grained difference discovery and iii) learn attention for specialized domains. Experiments on our three low-resource tasks demonstrate our proposals already provide a better baseline than transfer learning, data augmentation, and fine-grained methods. This highlights the unique characteristics and challenges of low-resource vision for foundation models that warrant further investigation. Project page: https://xiaobai1217.github.io/Low-Resource-Vision/. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Retrieval on Historic Map (test)](): Image Retrieval; Historic Map (test); R@1: 37.1. - [Image Retrieval on Mechanical Drawing (test)](): Image Retrieval; Mechanical Drawing (test); R@1: 60.7. - [Image Classification on Circuit Diagram (test)](): Image Classification; Circuit Diagram (test); Top-1 Accuracy: 24.1. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()