Semantic bottleneck for computer vision tasks
It addresses the need for interpretable AI in computer vision, making models more understandable for users, though it appears incremental by applying a novel method to an existing bottleneck.
The paper tackles the problem of computation intelligibility in computer vision by introducing a semantic bottleneck that represents images entirely in natural language, achieving state-of-the-art results in semantic content-based image retrieval and strong performance in image classification.
This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks. More specifically, our proposition is to introduce what we call a semantic bottleneck in the processing pipeline, which is a crossing point in which the representation of the image is entirely expressed with natural language , while retaining the efficiency of numerical representations. We show that our approach is able to generate semantic representations that give state-of-the-art results on semantic content-based image retrieval and also perform very well on image classification tasks. Intelligibility is evaluated through user centered experiments for failure detection.