ExpNet: A unified network for Expert-Level Classification

TL;DR

ExpNet is a unified neural network architecture designed for expert-level classification tasks, effectively handling hierarchical features and part-global correlations, and demonstrating superior performance across diverse fields.

Contribution

The paper introduces ExpNet, a novel hierarchical network with Gaze-Shift attention mechanism for unified expert-level classification.

Findings

Outperforms state-of-the-art methods in FGVC, disease, and artwork classification

Effectively models part-global correlations and hierarchical features

Demonstrates strong generalization across different expert-level tasks

Abstract

Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them expert-level classification. Previous fine-grained vision classification (FGVC) has made many efforts on some of its specific sub-tasks. However, they are difficult to expand to the general cases which rely on the comprehensive analysis of part-global correlation and the hierarchical features interaction. In this paper, we propose Expert Network (ExpNet) to address the unique challenges of expert-level classification through a unified network. In ExpNet, we hierarchically decouple the part and context features and individually process them using a novel attentive mechanism, called Gaze-Shift. In each stage, Gaze-Shift produces a focal-part feature for the subsequent abstraction and memorizes a context-related embedding. Then we fuse the final focal embedding with all memorized context-related embedding to make the prediction. Such an architecture realizes the dual-track processing of partial and global information and hierarchical feature interactions. We conduct the experiments over three representative expert-level classification tasks: FGVC, disease classification, and artwork attributes classification. In these experiments, superior performance of our ExpNet is observed comparing to the state-of-the-arts in a wide range of fields, indicating the effectiveness and generalization of our ExpNet. The code will be made publicly available.