Selecting Suitable Image Retargeting Methods with Multi-instance Multi-label Learning
نویسندگان
چکیده
Althogh the diversity of mobile devices brings in image retargeting technique to effectively display images on various screens, no existing image retargeting method can handle all images well. In this paper, we propose a novel approach to select suitable image retargeting methods solely based on original image characteristic, which can obtain acceptable selection accuracy with low computation cost. First, the original image is manually annotated with several simple features. Then, suitable methods are automatically selected from candidate image retargeting methods using multi-instance multi-label learning. Finally, target images are generated by the selected methods. Experiments demonstrate the effectiveness of the proposed approach.
منابع مشابه
Fully Convolutional Multi-Class Multiple Instance Learning
Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network. In this setting, we seek to learn a semantic segmentation model from just weak image-level labels. The model is trained...
متن کاملMulti-Instance Multi-Label Learning with Application to Scene Classification
In this paper, we formalize multi-instance multi-label learning, where each training example is associated with not only multiple instances but also multiple class labels. Such a problem can occur in many real-world tasks, e.g. an image usually contains multiple patches each of which can be described by a feature vector, and the image can belong to multiple categories since its semantics can be...
متن کاملImproving Multi-label Learning with Missing Labels by Structured Semantic Correlations
Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex image is very difficult, not only due to the intricacy of describing the image, but also because of the incompleteness nature of the observed labels. Existing w...
متن کاملInstance Similarity Deep Hashing for Multi-Label Image Retrieval
Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Recently, many deep hashing methods have been proposed and shown largely improved performance over traditional featurelearning-based methods. Most of these methods examine the pairwise similarity on the semantic-level labels, where the pairwise similarity is generally defined in a hard-a...
متن کاملMulti-Instance Multi-Label Learning with Weak Label
Multi-Instance Multi-Label learning (MIML) deals with data objects that are represented by a bag of instances and associated with a set of class labels simultaneously. Previous studies typically assume that for every training example, all positive labels are tagged whereas the untagged labels are all negative. In many real applications such as image annotation, however, the learning problem oft...
متن کامل