Corpus ID: 236318387

Learning Discriminative Representations for Multi-Label Image Recognition

  title={Learning Discriminative Representations for Multi-Label Image Recognition},
  author={Mohammed Hassanin and Ibrahim Radwan and Salman Khan and Murat Tahtali},
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… Expand

Figures and Tables from this paper


Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification
Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance, and significantly outperforms state-of-the-arts and has strong generalization capability. Expand
CNN-RNN: A Unified Framework for Multi-label Image Classification
The proposed CNN-RNN framework learns a joint image-label embedding to characterize the semantic label dependency as well as the image- label relevance, and it can be trained end-to-end from scratch to integrate both information in a unified framework. Expand
Exploit Bounding Box Annotations for Multi-Label Object Recognition
This paper first extracts object proposals from each image, then proposes to make use of ground-truth bounding box annotations (strong labels) to add another level of local information by using nearest-neighbor relationships of local regions to form a multi-view pipeline. Expand
A Discriminative Feature Learning Approach for Deep Face Recognition
This paper proposes a new supervision signal, called center loss, for face recognition task, which simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers. Expand
Beyond Object Proposals: Random Crop Pooling for Multi-Label Image Recognition
This paper proposes an object-proposal-free framework for multi-label image recognition: random crop pooling (RCP), which performs stochastic scaling and cropping over images before feeding them to a standard convolutional neural network, which works quite well with a max-pooling operation for recognizing the complex contents of multi- label images. Expand
Multi-label Image Recognition by Recurrently Discovering Attentional Regions
This work achieves the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module that demonstrates superior performances over other existing state-of-the-arts in both accuracy and efficiency. Expand
Multilabel Image Classification With Regional Latent Semantic Dependencies
The proposed RLSD achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurring in the images, and can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world. Expand
Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition
A recurrent attention reinforcement learning framework to iteratively discover a sequence of attentional and informative regions that are related to different semantic objects and further predict label scores conditioned on these regions to facilitate multi-label recognition. Expand
Multi-Label Image Recognition With Graph Convolutional Networks
This work proposes a multi-label classification model based on Graph Convolutional Network (GCN), and proposes a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN. Expand
Correlative multi-label multi-instance image annotation
A novel method is developed for achieving multi-label multi-instance image annotation, where image-level (bag-level) labels and region- level (instance- level) labels are both obtained and the associations between semantic concepts and visual features are mined both at the image level and at the region level. Expand