Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition
This addresses the problem of limited scalability and generalizability in fine-grained vision classification for professionals in fields like fashion, medicine, and art.
The paper tackles the challenge of professional visual recognition tasks requiring specialized categories by introducing Pro-NeXt, a biologically-inspired model that achieves state-of-the-art performance across 12 datasets in 5 diverse domains, with scaling in depth and width consistently improving accuracy.
Some visual recognition tasks are more challenging then the general ones as they require professional categories of images. The previous efforts, like fine-grained vision classification, primarily introduced models tailored to specific tasks, like identifying bird species or car brands with limited scalability and generalizability. This paper aims to design a scalable and explainable model to solve Professional Visual Recognition tasks from a generic standpoint. We introduce a biologically-inspired structure named Pro-NeXt and reveal that Pro-NeXt exhibits substantial generalizability across diverse professional fields such as fashion, medicine, and art-areas previously considered disparate. Our basic-sized Pro-NeXt-B surpasses all preceding task-specific models across 12 distinct datasets within 5 diverse domains. Furthermore, we find its good scaling property that scaling up Pro-NeXt in depth and width with increasing GFlops can consistently enhances its accuracy. Beyond scalability and adaptability, the intermediate features of Pro-NeXt achieve reliable object detection and segmentation performance without extra training, highlighting its solid explainability. We will release the code to foster further research in this area.