Learning Image Conditioned Label Space for Multilabel Classification
arXiv:1802.07460
Abstract
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.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Efficient Estimation of Word Representations in Vector Space
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- CNN: Single-label to Multi-label
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Deep Convolutional Ranking for Multilabel Image Annotation
- Multi-Instance Visual-Semantic Embedding