CVLGIVMLJun 16, 2020

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

arXiv:2006.08939v2102 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of subtle appearance differences in fine-grained objects for zero-shot learning, representing an incremental improvement over existing methods.

The paper tackles the problem of zero-shot object recognition in fine-grained categories by learning redundancy-free features to reduce superfluous information, achieving competitive results on four benchmark datasets.

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of different fine-grained objects tend to merely exhibit subtle differences in appearance, which will severely deteriorate zero-shot object recognition. To reduce the superfluous information in the fine-grained objects, in this paper, we propose to learn the redundancy-free features for generalized zero-shot learning. We achieve our motivation by projecting the original visual features into a new (redundancy-free) feature space and then restricting the statistical dependence between these two feature spaces. Furthermore, we require the projected features to keep and even strengthen the category relationship in the redundancy-free feature space. In this way, we can remove the redundant information from the visual features without losing the discriminative information. We extensively evaluate the performance on four benchmark datasets. The results show that our redundancy-free feature based generalized zero-shot learning (RFF-GZSL) approach can achieve competitive results compared with the state-of-the-arts.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes