Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels

TL;DR

This paper introduces a dual-perspective semantic-aware representation blending method for multi-label image recognition with partial labels, effectively transferring label information across images and categories to improve performance.

Contribution

The paper proposes a novel dual-perspective blending approach that leverages instance and prototype representations to enhance label prediction in partially labeled datasets.

Findings

Outperforms state-of-the-art algorithms on MS-COCO, Visual Genome, and Pascal VOC 2007.

Effective across various known label proportion settings.

Improves unknown label prediction accuracy.

Abstract

Despite achieving impressive progress, current multi-label image recognition (MLR) algorithms heavily depend on large-scale datasets with complete labels, making collecting large-scale datasets extremely time-consuming and labor-intensive. Training the multi-label image recognition models with partial labels (MLR-PL) is an alternative way, in which merely some labels are known while others are unknown for each image. However, current MLP-PL algorithms rely on pre-trained image similarity models or iteratively updating the image classification models to generate pseudo labels for the unknown labels. Thus, they depend on a certain amount of annotations and inevitably suffer from obvious performance drops, especially when the known label proportion is low. To address this dilemma, we propose a dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images, from instance and prototype perspective respectively, to transfer information of known labels to complement unknown labels. Specifically, an instance-perspective representation blending (IPRB) module is designed to blend the representations of the known labels in an image with the representations of the corresponding unknown labels in another image to complement these unknown labels. Meanwhile, a prototype-perspective representation blending (PPRB) module is introduced to learn more stable representation prototypes for each category and blends the representation of unknown labels with the prototypes of corresponding labels, in a location-sensitive manner, to complement these unknown labels. Extensive experiments on the MS-COCO, Visual Genome, and Pascal VOC 2007 datasets show that the proposed DSRB consistently outperforms current state-of-the-art algorithms on all known label proportion settings.