Learning Discriminative Representations for Multi-Label Image Recognition

07/23/2021
by   Mohammed Hassanin, et al.
17

Multi-label recognition is a fundamental, and yet is a challenging task in computer vision. Recently, deep learning models have achieved great progress towards learning discriminative features from input images. However, conventional approaches are unable to model the inter-class discrepancies among features in multi-label images, since they are designed to work for image-level feature discrimination. In this paper, we propose a unified deep network to learn discriminative features for the multi-label task. Given a multi-label image, the proposed method first disentangles features corresponding to different classes. Then, it discriminates between these classes via increasing the inter-class distance while decreasing the intra-class differences in the output space. By regularizing the whole network with the proposed loss, the performance of applying the wellknown ResNet-101 is improved significantly. Extensive experiments have been performed on COCO-2014, VOC2007 and VOC2012 datasets, which demonstrate that the proposed method outperforms state-of-the-art approaches by a significant margin of 3:5 dataset. Moreover, analysis of the discriminative feature learning approach shows that it can be plugged into various types of multi-label methods as a general module.

READ FULL TEXT

page 2

page 5

page 14

page 15

research
12/02/2022

Learning Disentangled Label Representations for Multi-label Classification

Although various methods have been proposed for multi-label classificati...
research
05/14/2022

Object-Aware Self-supervised Multi-Label Learning

Multi-label Learning on Image data has been widely exploited with deep l...
research
01/31/2021

MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images

For the sake of recognizing and classifying textile defects, deep learni...
research
10/27/2022

MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval

Instance-level image retrieval in fashion is a challenging issue owing t...
research
06/27/2012

Maximum Margin Output Coding

In this paper we study output coding for multi-label prediction. For a m...
research
07/04/2019

An External Knowledge Enhanced Multi-label Charge Prediction Approach with Label Number Learning

Multi-label charge prediction is a task to predict the corresponding acc...
research
06/08/2017

Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision

Scene labeling is a challenging classification problem where each input ...

Please sign up or login with your details

Forgot password? Click here to reset