Learning Image Conditioned Label Space for Multilabel Classification
This addresses multilabel classification for image analysis, offering an incremental improvement in efficiency and performance.
The paper tackles multilabel image classification by proposing an image-dependent ranking model that learns a mapping to differentiate relevant and irrelevant labels, achieving state-of-the-art performance on a public benchmark dataset with fewer training images.
This work addresses the task of multilabel image classification. Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. Specifically, we propose an image-dependent ranking model, which returns a ranked list of labels according to its relevance to the input image. In contrast to conventional CNN models that learn an image representation (i.e. the image embedding vector), the developed model learns a mapping (i.e. a transformation matrix) from an image in an attempt to differentiate between its relevant and irrelevant labels. Despite the conceptual simplicity of our approach, experimental results on a public benchmark dataset demonstrate that the proposed model achieves state-of-the-art performance while using fewer training images than other multilabel classification methods.