Graph-RISE: Graph-Regularized Image Semantic Embedding

TL;DR

Graph-RISE introduces a large-scale neural graph learning framework for fine-grained image semantic embeddings, significantly improving discrimination of subtle semantic nuances in image retrieval and classification tasks.

Contribution

The paper presents Graph-RISE, a novel graph-regularized neural embedding method capable of handling over 40 million ultra-fine-grained labels, surpassing existing methods.

Findings

Outperforms state-of-the-art on image classification and ranking

Effectively captures nuanced semantic differences

Enhances image retrieval to reflect human-like perception

Abstract

Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking. We provide case studies to demonstrate that, qualitatively, image retrieval based on Graph-RISE effectively captures semantics and, compared to the state-of-the-art, differentiates nuances at levels that are closer to human-perception.