Edge-Guided Cross-Domain Learning with Shape Regression for Sketch-Based Image Retrieval
نویسندگان
چکیده
منابع مشابه
Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval
The key challenge for learning a fine-grained sketch-based image retrieval (FG-SBIR) model is to bridge the domain gap between photo and sketch. Existing models learn a deep joint embedding space with discriminative losses where a photo and a sketch can be compared. In this paper, we propose a novel discriminative-generative hybrid model by introducing a generative task of cross-domain image sy...
متن کاملDeep sketch feature for cross-domain image retrieval
Deep learning has been proven be very effective for various image recognition tasks, e.g., image classification, semantic segmentation, image retrieval, shape classification etc. However, existing works on deep learning for image recognition mainly focus on either natural image data or binary shape data. In this paper, we show that deep convolutional neural networks (DCNN) is also suitable for ...
متن کاملCross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval
In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting lowand mid-level descriptors for direct feature matching, recent works have shown the benefit of learning coupled feature representations to describe data from two related sources. However, cross-domain representation learni...
متن کاملSketch Based Image Retrieval
Sketch based image retrieval is a task that has been explored a lot recently as an alternative method for image retrieval. We develop this task on The Sketchy Database, where we use Siamese and Triplet network to perform sketch based image retrieval. We employ deep residual learning network as the constituent network in the Siamese and Triplet architecture and use new data augmentation techniqu...
متن کاملSketch Based Image Retrieval
The content based image retrieval (CBIR) is one of the most common, increasing research areas of the digital image processing. Most of the existing image search tools, such as Google Images as well as Yahoo! Image search, are built on textual annotation of images. In these tools, images are physically annotated with keywords and then retrieved using text-based search methods. The presentations ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2019
ISSN: 2169-3536
DOI: 10.1109/access.2019.2903534