Published on Wed Feb 21 2018

Learning Image Conditioned Label Space for Multilabel Classification

Yi-Nan Li, Mei-Chen Yeh

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 propose an image-dependent ranking model.

0
0
0
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.

Fri Apr 15 2016
Neural Networks
CNN-RNN: A Unified Framework for Multi-label Image Classification
Traditional approaches to multi-label image classification learn independent classifiers for each category. The proposed CNN-RNN framework learns a joint image-label embedding. It can be trained end-to-end from scratch to integrate both information in a unified framework.
0
0
0
Tue Apr 11 2017
Computer Vision
Improving Pairwise Ranking for Multi-label Image Classification
Pairwise ranking has been successful in multi-label image classification. Most existing approaches use the hinge loss to train their models. This loss is non-smooth and thus is difficult to optimize. We propose a novel loss function for pairwise ranking, which is smooth everywhere.
0
0
0
Tue Dec 17 2013
Computer Vision
Deep Convolutional Ranking for Multilabel Image Annotation
Multilabel image annotation is one of the most important challenges in computer vision. Deep Neural Networks have shown potential to significantly boost performance. Our experiments on the NUS-WIDE dataset outperforms the conventional visual features by about 10%.
0
0
0
Tue Aug 24 2021
Machine Learning
sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification
Multiclass multilabel classification refers to the task of attributing multiple labels to examples via predictions. We propose a loss function, sigmoidF1. It is an approximation of the F1 score that is smooth and tractable for stochastic gradient descent. We show that any confusion matrix metric can be formulated with a smooth surrogate.
0
0
0
Tue Oct 08 2013
Machine Learning
Fast Multi-Instance Multi-Label Learning
Multi-instance multi-label learning (MIML) problems have been extensively studied. MIMLfast is able to exploit label relations with shared space and discover sub-concepts for complicated labels. On a larger data set where none of existing approaches can return results in 24 hours, MIMlfast takes only 12
0
0
0
Fri Jul 23 2021
Computer Vision
Learning Discriminative Representations for Multi-Label Image Recognition
Multi-label recognition is a fundamental, and yet is a challenging task in computer vision. We propose a unified deep network to learn discriminative features for the multi-label task. The proposed method disentangles features corresponding to different classes. Then, it discriminates between these classes via
2
1
0