FETA: Towards Specializing Foundation Models for Expert Task Applications



Published on




Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we show in this paper, FMs still have poor out-of-the-box performance on expert tasks (e.g. retrieval of car manuals technical illustrations from language queries), data for which is either unseen or belonging to a long-tail part of the data distribution of the huge datasets used for FM pre-training. This underlines the necessity to explicitly evaluate and finetune FMs on such expert tasks, arguably ones that appear the most in practical real-world applications. In this paper, we propose a first of its kind FETA benchmark built around the task of teaching FMs to understand technical documentation, via learning to match their graphical illustrations to corresponding language descriptions. Our FETA benchmark focuses on text-to-image and image-to-text retrieval in public car manuals and sales catalogue brochures. FETA is equipped with a procedure for completely automatic annotation extractaion, allowing easy extension of FETA to more documentation types and application domains in the future. Our automatic annotation leads to an automated performance metric shown to be consistent with metrics computed on human-curated annotations (also released). We provide multiple baselines and analysis of popular FMs on FETA leading to several interesting findings that we believe would be very valuable to the FM community, paving the way towards real-world application of FMs for practical expert tasks currently “overlooked” by standard benchmarks focusing on common objects.

Please cite our work using the BibTeX below.

title={{FETA}: Towards Specializing Foundational Models for Expert Task Applications},
author={Amit Alfassy and Assaf Arbelle and Oshri Halimi and Sivan Harary and Roei Herzig and Eli Schwartz and Rameswar Panda and Michele Dolfi and Christoph Auer and Peter W. J. Staar and Kate Saenko and Rogerio Feris and Leonid Karlinsky},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
Close Modal