Filters








9,893 Hits in 4.0 sec

One-Shot Fine-Grained Instance Retrieval [article]

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
2017 arXiv   pre-print
Fine-Grained Visual Categorization (FGVC) has achieved significant progress recently.  ...  Finally, we present a coarse-to-fine retrieval framework consisting of three components, i.e., coarse retrieval, fine-grained retrieval, and query expansion, respectively.  ...  Fine-Grained Visual Categorization: In the past ve years, researchers have signi cantly boosted the classi cation accuracy of FGVC.  ... 
arXiv:1707.00811v1 fatcat:zfnpunlofrbspkgpz755xe5p2a

StackDRL: Stacked Deep Reinforcement Learning for Fine-grained Visual Categorization

Xiangteng He, Yuxin Peng, Junjie Zhao
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Fine-grained visual categorization (FGVC) is the discrimination of similar subcategories, whose main challenge is to localize the quite subtle visual distinctions between similar subcategories.  ...  Semantic reward function drives StackDRL to fully learn the discriminative and conceptual visual information, via jointly combining the attention-based reward and category-based reward.  ...  But the CNN, which is used to extract the attention map for each image, while is not fine-tuned on the specific fine-grained visual categorization dataset.  ... 
doi:10.24963/ijcai.2018/103 dblp:conf/ijcai/HePZ18 fatcat:yjlj4azwafgxzcllwugpfjatzu

Adversarial Networks with Circular Attention Mechanism for Fine-Grained Domain Adaptation

Ningyu He, Jie Zhu
2021 IEEE Access  
This paper presents the circular attention mechanism to cyclically extract deep-level image features to match the label hierarchy from coarse to fine.  ...  An effective solution is to apply the domain adaptation (DA) method to transfer knowledge from existing fine-grained image datasets to massive unlabeled data.  ...  CUB-200-2011 is the most widely used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds.  ... 
doi:10.1109/access.2021.3118786 fatcat:kgdhxxzdqzdilbhmbgft3ixvvy

Multiple Granularity Descriptors for Fine-Grained Categorization

Dequan Wang, Zhiqiang Shen, Jie Shao, Wei Zhang, Xiangyang Xue, Zheng Zhang
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.  ...  This is due to two main issues: how to localize discriminative regions for recognition and how to learn sophisticated features for representation.  ...  Acknowledgements We would like to thank anonymous reviewers for helpful feedback. We would also like to thank Tianjun Xiao and Hao Ye for useful discussions.  ... 
doi:10.1109/iccv.2015.276 dblp:conf/iccv/WangSSZXZ15 fatcat:uccgg6vquzhbxoghp77y6txjvm

One-Shot Fine-Grained Instance Retrieval

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Fine-Grained Visual Categorization (FGVC) has achieved signicant progress recently.  ...  Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).  ...  INTRODUCTION Di erent from conventional object categorization, Fine-Grained Visual Categorization (FGVC) aims to identify objects belonging to the same or closely-related species that only experienced  ... 
doi:10.1145/3123266.3123278 dblp:conf/mm/YaoZZLT17 fatcat:s6stj7xujzganjypus6l2phive

Discriminative Cellets Discovery for Fine-Grained Image Categories Retrieval

Luming Zhang, Yi Yang, Roger Zimmermann
2014 Proceedings of International Conference on Multimedia Retrieval - ICMR '14  
On the basis of the feature vector built from the selected cellets, fine-grained image categorization is conducted by training a linear SVM.  ...  Fine-grained image categories recognition is a challenging task aiming at distinguishing objects belonging to the same basic-level category, such as leaf or mushroom.  ...  As the SPM only incorporate coarse visual cues for generic object recognition, models customized for fine-grained cate-gorization have been developed, focusing on discovering tiny discriminative object  ... 
doi:10.1145/2578726.2578736 dblp:conf/mir/ZhangYZ14 fatcat:iumrwuj6szfmdjyfnix5lz4dgi

Usage of spatial scales for the categorization of faces, objects, and scenes

Donald J. Morrison, Philippe G. Schyns
2001 Psychonomic Bulletin & Review  
A coarse-to-fine bias exists at the first stage of description of the input (the primal sketch).  ...  information for categorization (i.e., a perceptually driven coarse-to-fine categorization scheme)?  ... 
doi:10.3758/bf03196180 pmid:11700896 fatcat:nwvm3xkvxngohmdmjq2yrv26oq

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity [article]

Dan Ruta, Saeid Motiian, Baldo Faieta, Zhe Lin, Hailin Jin, Alex Filipkowski, Andrew Gilbert, John Collomosse
2021 arXiv   pre-print
ALADIN sets a new state of the art accuracy for style-based visual search over both coarse labelled style data (BAM) and BAM-FG; a new 2.62 million image dataset of 310,000 fine-grained style groupings  ...  ALADIN takes a weakly supervised approach to learning a representation for fine-grained style similarity of digital artworks, leveraging BAM-FG, a novel large-scale dataset of user generated content groupings  ...  Coarse (BAM/BAM-X) and Fine grained (BAM-FG) style discrimination for the ALADIN model compared to baselines on coarse and fine-grained retrieval (BAM-FG). The larger ALADIN-L model is used.  ... 
arXiv:2103.09776v1 fatcat:gddjgr4zcnetlp26aihmy2aerq

Coarse Blobs or Fine Edges? Evidence That Information Diagnosticity Changes the Perception of Complex Visual Stimuli

A Oliva
1997 Cognitive Psychology  
Experiment 1 tested whether coarse and fine spatial scales were both available at the onset of scene categorization.  ...  Efficient categorizations of complex visual stimuli require effective encodings of their distinctive properties.  ...  Secondly, the animations simultaneously presented a coarse-to-fine and a fine-to-coarse information sequence to the visual system (coarse-to-fine in LSF, and fine-to-coarse in HSF).  ... 
doi:10.1006/cogp.1997.0667 pmid:9325010 fatcat:74ysruoxyzfe5acqhco6dlo4o4

Classifying Object Manipulation Actions based on Grasp-types and Motion-Constraints [article]

Kartik Gupta, Darius Burschka, Arnav Bhavsar
2018 arXiv   pre-print
Our results justifies the efficacy of grasp attributes for the task of fine-grained and coarse-grained object manipulation action recognition.  ...  In this work, we address a challenging problem of fine-grained and coarse-grained recognition of object manipulation actions.  ...  Grasp attributes We propose to use coarse and fine level categorization of grasp types.  ... 
arXiv:1806.07574v1 fatcat:4vtq63rgxbbkjlr5zbalw2oufe

Downscaling land-use data to provide global 30″ estimates of five land-use classes

Andrew J. Hoskins, Alex Bush, James Gilmore, Tom Harwood, Lawrence N. Hudson, Chris Ware, Kristen J. Williams, Simon Ferrier
2016 Ecology and Evolution  
Furthermore, the general method presented here could be useful to others wishing to downscale similarly constrained coarse-resolution data for other environmental variables. 3040  ...  Application of the new method to all 61 biorealms produced global fine-grained layers from the 2005 time step of the Land-use Harmonization dataset.  ...  Downscaling algorithm Statistical downscaling uses statistical methods to translate relationships between coarse-grained response data and (multiple) fine-grained covariate data into fine-grained predictions  ... 
doi:10.1002/ece3.2104 pmid:27069595 pmcid:PMC4814442 fatcat:xm32fmtz4naofnbaomehv5fv3q

Refining Coarse-grained Spatial Data using Auxiliary Spatial Data Sets with Various Granularities [article]

Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa, Hiroyuki Toda
2019 arXiv   pre-print
We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets.  ...  We integrate the Gaussian process with a spatial aggregation process that transforms the fine-grained target data into the coarse-grained target data, by which we can infer the fine-grained target Gaussian  ...  Figures 3 and 4 visualize the predicted fine-grained target data z for the PM2.5 data set and for the poverty rate data set, respectively.  ... 
arXiv:1809.07952v2 fatcat:3yhwcixw6nbwlb3shol3gra7xy

Super-Fine Attributes with Crowd Prototyping

Daniel Martinho-Corbishley, Mark Nixon, John N. Carter
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We aim to discover more relevant and precise subject descriptions, improving image retrieval and closing the semantic gap.  ...  We also find our 3 super-fine traits to outperform 35 binary attributes by 6.5% mAP for subject retrieval in a challenging zero-shot identification scenario.  ...  Super-fine (red) labels on the PETA dataset. Conventional categories are coarse-grained and can be inconsistent and/or irrelevant.  ... 
doi:10.1109/tpami.2018.2836900 pmid:29994759 fatcat:z7cf52y4jrdmnl7fke5yvekshe

Room for improvement in automatic image description: an error analysis [article]

Emiel van Miltenburg, Desmond Elliott
2017 arXiv   pre-print
Our analysis operates on two levels: first we check the descriptions for accuracy, and then we categorize the types of errors we observe in the inaccurate descriptions.  ...  We find only 20% of the descriptions are free from errors, and surprisingly that 26% are unrelated to the image.  ...  Acknowledgments EM is supported by the Netherlands Organization for Scientific Research (NWO) via the Spinozaprize awarded to Piek Vossen (SPI 30-673, 2014(SPI 30-673, -2019.  ... 
arXiv:1704.04198v1 fatcat:746hx4m6gbdjjbxw4shgjw4jge

Literacy effects on language and vision: Emergent effects from an amodal shared resource (ASR) computational model

Alastair C. Smith, Padraic Monaghan, Falk Huettig
2014 Cognitive Psychology  
www.elsevier.com/locate/co gpsych phonological representations in the model simulated the high/low literacy effects on phonological processing, suggesting that literacy has a focused effect in changing the grain-size  ...  For each simulation set (fine grain, low efficiency; fine grain, high efficiency; moderate grain, low efficiency; moderate grain, high efficiency; coarse grain, low efficiency; coarse grain, high efficiency  ...  Fixation proportions are plotted for fine grain (Fine), moderate grain (Moderate) and coarse grain (Coarse) simulations with high cognitive efficiency (Fig. 3A ) and low cognitive efficiency ( Fig. 3B  ... 
doi:10.1016/j.cogpsych.2014.07.002 pmid:25171049 fatcat:t3vsytncnfgf3bsn2qh3nprgfe
« Previous Showing results 1 — 15 out of 9,893 results