Compact descriptors for sketch-based image retrieval using a triplet loss convolutional neural network.
Computer Vision and Image Understanding（2017）
摘要
•Sketch-based image retrieval with a half-shared triplet and a modified loss.•Generalisation capability and state-of-the-art performance.•Compact representation with 56-bit feature encoding.
更多查看译文
关键词
Sketch based image retrieval (SBIR),Deep learning,Triplet loss function,Cross-domain modelling,Compact feature representations
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要