Weakly Supervised Image Annotation and Segmentation with Objects and Attributes

TL;DR

This paper introduces a non-parametric Bayesian model that leverages weakly labeled images to jointly learn object and attribute appearances, their associations, and perform multiple vision tasks such as annotation, description, and segmentation.

Contribution

It presents a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors with explicit correlations, enabling comprehensive scene understanding.

Findings

Outperforms other weakly supervised methods on benchmark datasets.

Achieves results comparable to strongly supervised models in segmentation and annotation.

Effectively models object-attribute relationships for improved scene interpretation.

Abstract

We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr. Given weak image-level annotations of objects and attributes without locations or associations between them, our model aims to learn the appearance of object and attribute classes as well as their association on each object instance. Once learned, given an image, our model can be deployed to tackle a number of vision problems in a joint and coherent manner, including recognising objects in the scene (automatic object annotation), describing objects using their attributes (attribute prediction and association), and localising and delineating the objects (object detection and semantic segmentation). This is achieved by developing a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors and explicitly captures their correlations within and across superpixels. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model significantly outperforms weakly supervised alternatives and is often comparable with existing strongly supervised models on a variety of tasks including semantic segmentation, automatic image annotation and retrieval based on object-attribute associations.