Building a visual semantics aware object hierarchy
This addresses bias in computer vision tasks caused by linguistic annotations, potentially improving model accuracy for researchers and practitioners, though it appears incremental as it builds on existing hierarchy concepts.
The paper tackles the semantic gap problem in image annotations by proposing an unsupervised method to build a visual semantics aware object hierarchy, which aims to reduce bias and improve object recognition performance, with preliminary results showing efficiency and potential.
The semantic gap is defined as the difference between the linguistic representations of the same concept, which usually leads to misunderstanding between individuals with different knowledge backgrounds. Since linguistically annotated images are extensively used for training machine learning models, semantic gap problem (SGP) also results in inevitable bias on image annotations and further leads to poor performance on current computer vision tasks. To address this problem, we propose a novel unsupervised method to build visual semantics aware object hierarchy, aiming to get a classification model by learning from pure-visual information and to dissipate the bias of linguistic representations caused by SGP. Our intuition in this paper comes from real-world knowledge representation where concepts are hierarchically organized, and each concept can be described by a set of features rather than a linguistic annotation, namely visual semantic. The evaluation consists of two parts, firstly we apply the constructed hierarchy on the object recognition task and then we compare our visual hierarchy and existing lexical hierarchies to show the validity of our method. The preliminary results reveal the efficiency and potential of our proposed method.