2,457 Hits in 8.2 sec

Guided Zoom: Questioning Network Evidence for Fine-grained Classification [article]

Sarah Adel Bargal, Andrea Zunino, Vitali Petsiuk, Jianming Zhang, Kate Saenko, Vittorio Murino, Stan Sclaroff
2020 arXiv   pre-print
We show that Guided Zoom improves the classification accuracy of a deep convolutional neural network model and obtains state-of-the-art results on three fine-grained classification benchmark datasets.  ...  We propose Guided Zoom, an approach that utilizes spatial grounding of a model's decision to make more informed predictions.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
arXiv:1812.02626v2 fatcat:74dd2h3su5cnfp6xquqgefhd3e

Are CNN Predictions based on Reasonable Evidence?

Sarah Adel Bargal, Andrea Zunino, Vitali Petsiuk, Jianming Zhang, Kate Saenko, Vittorio Murino, Stan Sclaroff
2019 Computer Vision and Pattern Recognition  
We show that Guided Zoom results in the refinement of a model's classification accuracy on two fine-grained classification datasets.  ...  Guided Zoom questions how reasonable the evidence used to make a prediction is.  ...  By questioning network evidence, we demonstrate refined accuracy on two fine-grained classification benchmark datasets. Guided Zoom Evidence CNN.  ... 
dblp:conf/cvpr/BargalZPZSMS19 fatcat:nsgp63otszhxveygg4sf4ksrsi

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots [article]

Md Jahidul Islam, Ruobing Wang, Junaed Sattar
2022 arXiv   pre-print
This paper presents a holistic approach to saliency-guided visual attention modeling (SVAM) for use by autonomous underwater robots.  ...  The bottom-up branch performs a rough yet reasonably accurate saliency estimation at a fast rate, whereas the deeper top-down branch incorporates a residual refinement module (RRM) that provides fine-grained  ...  zoom into interesting image regions for detailed visual perception.  ... 
arXiv:2011.06252v2 fatcat:crctlr7i5jcqbdafbejg5ix7l4

Climate Models: A User's Guide

Daniel A. Farber
2007 Social Science Research Network  
You point and zoom to anyplace on the planet that you want to explore. Satellite images and local facts zoom into view. Tap into Google search to show local points of interest and facts.  ...  These technological advances allow models to be more fine-grained (smaller cells providing more detail on processes) and enable the incorporation of ocean currents and other factors too complex for the  ... 
doi:10.2139/ssrn.1030607 fatcat:wxbnffwy6jhldg2i7tidohfdwm

Decentralized control of automatic guided vehicles

Danny Weyns, Tom Holvoet, Kurt Schelfthout, Jan Wielemans
2008 Companion to the 23rd ACM SIGPLAN conference on Object oriented programming systems languages and applications - OOPSLA Companion '08  
Starting from system requirements, we give an overview of the software architecture and we zoom in on a number of concrete functionalities.  ...  An automatic guided vehicle (AGV) transportation system is a fully automated system that provides logistic services in an industrial environment such as a warehouse or a factory.  ...  Thanks to Tom Holvoet, Alexander Helleboogh, Nelis Boucke, Wannes Schols and Bart Demarsin for the collaboration in the EMC 2 project.  ... 
doi:10.1145/1449814.1449819 dblp:conf/oopsla/WeynsHSW08 fatcat:xx4ciccekjautctyvovmn6dtie

Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations [article]

Hanxiao Wang, Venkatesh Saligrama, Stan Sclaroff, Vitaly Ablavsky
2019 arXiv   pre-print
To deal with fine-grained classification, we adopt the perspective of sequential fixation with a foveated field-of-view to model cloud-edge interactions.  ...  In addition, we propose to shape the reward to provide informative feedback after each fixation to better guide RL training.  ...  Specifically, we use DRIFT's hard attentions to zoom into the original images (Fig. 6 ).  ... 
arXiv:1811.06868v2 fatcat:lfvxyj7awfg5plpknmed77dw6m

What do you really want to do? Towards a Theory of Intentions for Human-Robot Collaboration

Rocio Gomez, Mohan Sridharan, Heather Riley
2020 Annals of Mathematics and Artificial Intelligence  
-After refinement, each zone is magnified to obtain grid cells. Also, each object is magnified into parts such as base and top after refinement.  ...  In what follows, we use "refinement and zooming" to refer to the use of both refinement and zooming as described above.  ... 
doi:10.1007/s10472-019-09672-4 fatcat:5y3wv5ueqbbrligw4l2ftkvh2i

Introduction [chapter]

Darren R. Reid, Brett Sanders
2021 Open Field Guides  
This license allows you to share, copy, distribute and transmit the text; to adapt the text for non-commercial purposes of the text providing attribution is made to the authors (but not in any way that  ...  In this model, interviewees appear to shape and guide the piece's thesis, though that is almost certainly not the case.  ...  purchasing decision.  ... 
doi:10.11647/obp.0255.25 fatcat:u62g4d43ybhx7ayyehgvcueomm

Towards a Theory of Intentions for Human-Robot Collaboration [article]

Rocio Gomez, Mohan Sridharan, Heather Riley
2019 arXiv   pre-print
Each abstract action is implemented as a sequence of concrete actions by automatically zooming to and reasoning with the part of the fine-resolution transition diagram relevant to the current coarse-resolution  ...  Each concrete action in this sequence is executed using probabilistic models of the uncertainty in sensing and actuation, and the corresponding fine-resolution outcomes are used to infer coarse-resolution  ...  Acknowledgements The authors thank Michael Gelfond for discussions related to the modeling of defaults and exogenous actions in the architecture reported in this paper.  ... 
arXiv:1907.13275v1 fatcat:k7m7f4takrarlhppbs5ikrmkb4

Visual Concept Recognition and Localization via Iterative Introspection [article]

Amir Rosenfeld, Shimon Ullman
2016 arXiv   pre-print
Class Activation Mapping (CAM) is a recent method that makes it possible to easily highlight the image regions contributing to a network's classification decision.  ...  We build upon these two developments to enable a network to re-examine informative image regions, which we term introspection.  ...  As shown, our method is particularly beneficial for fine-grained tasks such as species [4, 5] or model [6] identification and to challenging cases in e.g., action recognition [7] , which requires  ... 
arXiv:1603.04186v2 fatcat:lpiar5xzunf7raaxsolarmj654

The A to Z Guide to Accelerating Continuous Improvement with ResFrac [article]

Mark McClure, Garrett Fowler, Chris Hewson, Charles Kang
2022 arXiv   pre-print
Using ResFrac successfully requires high-level engineering skills: how to design and execute a modeling workflow, how to think critically about problems, and how to communicate the results.  ...  This document is designed to give a new ResFrac user the tools that they need to succeed. It describes what ResFrac does and how to use it. We cover much more than just button pressing.  ...  'ResFrac Users Guide' -a one-hour intro video b. 'The Case for Planar Fracture Modeling' -the technical basis for why we use planar fracture modeling, rather than complex fracture network modeling c.  ... 
arXiv:2205.14820v1 fatcat:s2k5tsdtwjbgnljs3exvi7csty

Travel Guides for Creative Tourists, Powered by Geotagged Social Media [article]

Dan Tasse, Jason I. Hong
2021 arXiv   pre-print
Current tools and guides typically provide them with lists of sights to see, which do not meet their needs. Manually building new tools for them would not scale.  ...  want to know about.  ...  STUDY 2: SURVEY TO REFINE TOURIST NEEDS MODEL To refine our model after Study 1, we conducted a survey.  ... 
arXiv:2112.12009v1 fatcat:uizyl2yl6nh5jjjfxzbvrvjita

SALISA: Saliency-based Input Sampling for Efficient Video Object Detection [article]

Babak Ehteshami Bejnordi, Amirhossein Habibian, Fatih Porikli, Amir Ghodrati
2022 arXiv   pre-print
paper, we propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection that allows for heavy down-sampling of unimportant background regions while preserving the fine-grained  ...  To achieve this, we propose a differentiable resampling module based on a thin plate spline spatial transformer network (TPS-STN).  ...  One way to tackle this problem is to use hierarchical representations. [38, 13, 32, 9] introduce hierarchical methods to refine the processing of a high-resolution image by adaptively zooming into their  ... 
arXiv:2204.02397v1 fatcat:xsv5rt5eqnfbjehr6wly3m5puy

The Hitchhiker's Guide to Neurophenomenology – The Case of Studying Self Boundaries With Meditators

Aviva Berkovich-Ohana, Yair Dor-Ziderman, Fynn-Mathis Trautwein, Yoav Schweitzer, Ohad Nave, Stephen Fulder, Yochai Ataria
2020 Frontiers in Psychology  
This paper is a practical guide to neurophenomenology.  ...  In the second part of the paper, we demonstrate how the theory can be put into practice by describing a decade of neurophenomenological studies investigating the sense of self with increasing focus on  ...  This full-blown NRP project attempts to implement all the proposed bridges: (1) Front-loading 1P insights to 3P study design -building on the fine-grained phenomenological analysis from the previous case  ... 
doi:10.3389/fpsyg.2020.01680 pmid:32793056 pmcid:PMC7385412 fatcat:gl5tel3z3nfrnfhxn2l52l2kru

The effect of team feedback and guided reflexivity on team performance change

Catherine Gabelica, P. Van den Bossche, S. De Maeyer, M. Segers, Wim Gijselaers
2014 Learning and Instruction  
clear decisions about ways to tackle their task.  ...  When looking into individual behaviours, teams exhibited more reflective behaviours during action over time, while their reflective behaviours during feedback did not change, demonstrating a suboptimal  ...  Acknowledgements The authors are very grateful to the two coders of the present study, Claudia Baudewijns and Lubomira Nikolova.  ... 
doi:10.1016/j.learninstruc.2014.09.001 fatcat:3rxlvf5k7fet5ednljyr4wurze
« Previous Showing results 1 — 15 out of 2,457 results