CVNov 10, 2018

Multi-label Object Attribute Classification using a Convolutional Neural Network

arXiv:1811.04309v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of classifying object attributes like color and shape to help handle unknown objects, but it is incremental as it builds on existing networks.

The paper tackles the problem of multi-label object attribute classification by proposing a Deep Attribute Network (DAN), which modifies and fine-tunes an existing object recognition network, and achieves better results compared to state-of-the-art methods on the ImageNet Attribute and a-Pascal datasets.

Objects of different classes can be described using a limited number of attributes such as color, shape, pattern, and texture. Learning to detect object attributes instead of only detecting objects can be helpful in dealing with a priori unknown objects. With this inspiration, a deep convolutional neural network for low-level object attribute classification, called the Deep Attribute Network (DAN), is proposed. Since object features are implicitly learned by object recognition networks, one such existing network is modified and fine-tuned for developing DAN. The performance of DAN is evaluated on the ImageNet Attribute and a-Pascal datasets. Experiments show that in comparison with state-of-the-art methods, the proposed model achieves better results.

Foundations

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

Your Notes