GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning

TL;DR

This paper introduces GBE-MLZSL, a novel framework for multi-label zero-shot learning that effectively integrates local and global features to improve recognition of unseen classes, demonstrating superior performance on benchmark datasets.

Contribution

The paper proposes a group bi-enhancement framework that combines local feature distinction and global feature preservation for more accurate MLZSL.

Findings

Outperforms state-of-the-art methods on NUS-WIDE dataset

Achieves significant accuracy improvements on Open-Images-v4

Demonstrates robustness in recognizing multiple unseen classes

Abstract

This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary knowledge, e.g., semantic information. Existing methods usually resort to analyzing the relationship of various seen classes residing in a sample from the dimension of spatial or semantic characteristics, and transfer the learned model to unseen ones. But they ignore the effective integration of local and global features. That is, in the process of inferring unseen classes, global features represent the principal direction of the image in the feature space, while local features should maintain uniqueness within a certain range. This integrated neglect will make the model lose its grasp of the main components of the image. Relying only on the local existence of seen classes during the inference stage introduces unavoidable bias. In this paper, we propose a novel and effective group bi-enhancement framework for MLZSL, dubbed GBE-MLZSL, to fully make use of such properties and enable a more accurate and robust visual-semantic projection. Specifically, we split the feature maps into several feature groups, of which each feature group can be trained independently with the Local Information Distinguishing Module (LID) to ensure uniqueness. Meanwhile, a Global Enhancement Module (GEM) is designed to preserve the principal direction. Besides, a static graph structure is designed to construct the correlation of local features. Experiments on large-scale MLZSL benchmark datasets NUS-WIDE and Open-Images-v4 demonstrate that the proposed GBE-MLZSL outperforms other state-of-the-art methods with large margins.