paper-with-me

홈 › Papers

What Makes Objects Similar: A Unified Multi-Metric Learning Approach

2016-12-01 · NeurIPS 2016 12 · Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang, Zhi-Hua Zhou

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Metric Learning

Similar Papers 제목 키워드 기반

A Method For Adding Motion-Blur on Arbitrary Objects By using Auto-Segmentation and Color Compensation Techniques

2021-09-22 · Michihiro Mikamo, Ryo Furukawa, Hiroshi Kawasaki

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

2019-07-25 · ICCV 2019 10 · Ahmed Samy Nassar, Sebastien Lefevre, Jan D. Wegner

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 Detection

What Remains of Visual Semantic Embeddings

2021-07-26 · Yue Jiao, Jonathon Hare, Adam Prügel-Bennett

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 Learning

Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation

2021-05-24 · CVPR 2021 1 · Tao Tu, Qing Ping, Govind Thattai, Gokhan Tur 외

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 Grounding

Cognitive residues of similarity

2013-08-09 · Stephanie OToole, Mark T. Keane

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