Sketch-a-Net that Beats Humans
نویسندگان
چکیده
Deep Neural Networks (DNNs) have recently outperformed traditional object recognition algorithms on multiple largescale datasets, such as ImageNet. However, the model trained on ImageNet fails on recognising the sketches, because the data source is dominated by photos and all kinds of sketches are roughly labelled as ‘cartoon’ rather than their own categorises (e.g., ‘cat’). Most of sketch recognition methods still heavily rely on the hand-craft feature extraction techniques, thus it is interesting to know whether DNNs can eliminate the needs of specific feature engineering in this area, and how the architecture is designed for sketch recognition purpose. To the best of our knowledge, it is the first deep neural network model for sketch classification, and it has outperformed stateof-the-art results in the TU-Berlin sketch benchmark. Based on that, we outline a sketch image retrieval system in a unified neural network framework.
منابع مشابه
شریعت - شهر اسلامی
Although in the structural approaches to the concept of place identity, various aspects of the built environment, natural environment, social environment and human activities are considered as the factors of the city identifying. In the normative approaches, adaptation of the socio-spatial structure of the city with the values, culture and human needs have major contribution in its identity. Wi...
متن کاملGeosemantic Snapping for Sketch-Based Modeling
Modeling 3D objects from sketches is a process that requires several challenging problems including segmentation, recognition and reconstruction. Some of these tasks are harder for humans and some are harder for the machine. At the core of the problem lies the need for semantic understanding of the shape’s geometry from the sketch. In this paper we propose a method to model 3D objects from sket...
متن کاملPhenotypical evidence for a gender difference in cardiac norepinephrine transporter function.
Norepinephrine transporter (NET) function has a central role in the regulation of synaptic norepinephrine concentrations. Clinical observations in orthostatic intolerance patients suggest a gender difference in NET function. We compared the cardiovascular response to selective NET inhibition with reboxetine between 12 healthy men and 12 age-matched women. Finger blood pressure, brachial blood p...
متن کاملSketch Learning by Analogy
Sketches are shapes that represent objects, scenes, or ideas by depicting relevant parts and their spatial arrangements. While humans are quite e cient in understanding and using sketch drawings, those are largely inaccessible to computers. We argue that this is due to a specific shape based representation by humans and hence the use of cognitively inspired representation and reasoning techniqu...
متن کامل