Timezone: »
Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric. To make learning more effective and efficient, hard sample mining is usually employed, with samples identified through computing the Euclidean feature distance. However, the global Euclidean distance cannot faithfully characterize the true feature similarity in a complex visual feature space, where the intraclass distance in a high-density region may be larger than the interclass distance in low-density regions. In this paper, we introduce a Position-Dependent Deep Metric (PDDM) unit, which is capable of learning a similarity metric adaptive to local feature structure. The metric can be used to select genuinely hard samples in a local neighborhood to guide the deep embedding learning in an online and robust manner. The new layer is appealing in that it is pluggable to any convolutional networks and is trained end-to-end. Our local similarity-aware feature embedding not only demonstrates faster convergence and boosted performance on two complex image retrieval datasets, its large margin nature also leads to superior generalization results under the large and open set scenarios of transfer learning and zero-shot learning on ImageNet 2010 and ImageNet-10K datasets.
Author Information
Chen Huang (Chinese University of HongKong)
Chen Change Loy (The Chinese University of HK)
Xiaoou Tang (The Chinese University of Hong Kong)
More from the Same Authors
-
2021 : Semi-Supervised Domain Generalization with Stochastic StyleMatch »
Kaiyang Zhou · Chen Change Loy · Ziwei Liu -
2021 Poster: A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis »
Xingang Pan · Xudong XU · Chen Change Loy · Christian Theobalt · Bo Dai -
2021 Poster: K-Net: Towards Unified Image Segmentation »
Wenwei Zhang · Jiangmiao Pang · Kai Chen · Chen Change Loy -
2021 Poster: Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data »
Liming Jiang · Bo Dai · Wayne Wu · Chen Change Loy -
2021 Poster: Unsupervised Object-Level Representation Learning from Scene Images »
Jiahao Xie · Xiaohang Zhan · Ziwei Liu · Yew Soon Ong · Chen Change Loy -
2014 Poster: Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations »
Zhenyao Zhu · Ping Luo · Xiaogang Wang · Xiaoou Tang -
2014 Poster: Deep Learning Face Representation by Joint Identification-Verification »
Yi Sun · Yuheng Chen · Xiaogang Wang · Xiaoou Tang -
2014 Poster: Zeta Hull Pursuits: Learning Nonconvex Data Hulls »
Yuanjun Xiong · Wei Liu · Deli Zhao · Xiaoou Tang -
2008 Poster: Cyclizing Clusters via Zeta Function of a Graph »
Deli Zhao · Xiaoou Tang