What Makes Objects Similar: A Unified Multi-Metric Learning Approach
Linkages are essentially determined by similarity measures that may be derived from multiple perspectives. For example, spatial linkages are usually generated based on localities of heterogeneous data, whereas semantic linkages can come from various properties, such as different physical meanings behind social relations. Many existing metric learning models focus on spatial linkages, but leave the rich semantic factors unconsidered. Similarities based on these models are usually overdetermined on linkages. We propose a Unified Multi-Metric Learning (UM2L) framework to exploit multiple types of metrics. In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages. Besides, we propose a uniform solver for UM2L which is guaranteed to converge. Extensive experiments on diverse applications exhibit the superior classification performance and comprehensibility of UM2L. Visualization results also validate its ability on physical meanings discovery.
Code (0)
등록된 구현이 없습니다.
Tasks
Metric LearningSimilar Papers 제목 키워드 기반
A Method For Adding Motion-Blur on Arbitrary Objects By using Auto-Segmentation and Color Compensation Techniques
When dynamic objects are captured by a camera, motion blur inevitably occurs. Such a blur is sometimes considered as just a noise, however, it sometimes gives an important effect to add dynamism in the scene for photogra…
Simultaneous multi-view instance detection with learned geometric soft-constraints
We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes …
multi-view detectionObjectobject-detectionObject DetectionWhat Remains of Visual Semantic Embeddings
Zero shot learning (ZSL) has seen a surge in interest over the decade for its tight links with the mechanism making young children recognize novel objects. Although different paradigms of visual semantic embedding models…
Contrastive LearningZero-Shot LearningLearning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation
GuessWhat?! is a two-player visual dialog guessing game where player A asks a sequence of yes/no questions (Questioner) and makes a final guess (Guesser) about a target object in an image, based on answers from player B …
Referring ExpressionReferring Expression ComprehensionVisual DialogVisual GroundingCognitive residues of similarity
What are the cognitive after-effects of making a similarity judgement? What, cognitively, is left behind and what effect might these residues have on subsequent processing? In this paper, we probe for such after-effects …
Object