Filters








21,859 Hits in 4.5 sec

Classification-Specific Parts for Improving Fine-Grained Visual Categorization [article]

Dimitri Korsch, Paul Bodesheim, Joachim Denzler
2019 arXiv   pre-print
Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance.  ...  We show in our experiments on various widely-used fine-grained datasets the effectiveness of the mentioned part selection method in conjunction with the extracted part features.  ...  Conclusion In this paper, we proposed a weakly supervised classification-specific part estimation approach for fine-grained visual categorization.  ... 
arXiv:1909.07075v1 fatcat:v4qzn44shrd6bn2g4thvxwkaza

Part-Stacked CNN for Fine-Grained Visual Categorization [article]

Shaoli Huang, Zhe Xu,Dacheng Tao,Ya Zhang
2015 arXiv   pre-print
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy.  ...  In this paper, we propose a novel Part-Stacked CNN architecture that explicitly explains the fine-grained recognition process by modeling subtle differences from object parts.  ...  Model interpretation The proposed approach adopts a part-based strategy to provide visual manuals for fine-grained visual categorization.  ... 
arXiv:1512.08086v1 fatcat:f5n6un6jw5gznjqcrrsctjzxhi

Fine-grained Classification via Categorical Memory Networks [article]

Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng
2020 arXiv   pre-print
Motivated by the desire to exploit patterns shared across classes, we present a simple yet effective class-specific memory module for fine-grained feature learning.  ...  The original and response features are combined to produce an augmented feature for classification.  ...  Architecture of Categorical Memory Network (CMN) for fine-grained classification.  ... 
arXiv:2012.06793v1 fatcat:csxxhxynuzdnbmnxhznczbiiqy

Part-Stacked CNN for Fine-Grained Visual Categorization

Shaoli Huang, Zhe Xu, Dacheng Tao, Ya Zhang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy.  ...  Based on manually-labeled strong part annotations, the proposed architecture consists of a fully convolutional network to locate multiple object parts and a two-stream classification network that encodes  ...  In this paper, we propose a new part-based CNN architecture for fine-grained visual categorization that models multiple object parts in a unified framework with high efficiency.  ... 
doi:10.1109/cvpr.2016.132 dblp:conf/cvpr/HuangXTZ16 fatcat:bc2zb23bpzbhrf3wq47r5mtlha

Fine-Grained Categorization for 3D Scene Understanding

Michael Stark, Jonathan Krause, Bojan Pepik, David Meger, James Little, Bernt Schiele, Daphne Koller
2012 Procedings of the British Machine Vision Conference 2012  
To that end, we propose two novel methods for fine-grained classification, both based on part information, as well as a new fine-grained category data set of car types.  ...  Fine-grained categorization of object classes is receiving increased attention, since it promises to automate classification tasks that are difficult even for humans, such as the distinction between different  ...  This material is based upon work supported by the Max Planck Center for Visual Computing and Communication and the Defense Advanced Research Projects Agency under Contract No. FA8650-10-C-7020.  ... 
doi:10.5244/c.26.36 dblp:conf/bmvc/StarkKPMLSK12 fatcat:inz6sn2befhutkfz333wb52tsi

Embedding Label Structures for Fine-Grained Feature Representation

Xiaofan Zhang, Feng Zhou, Yuanqing Lin, Shaoting Zhang
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Bilinear cnn mod- mentation and part localization for fine-grained categoriza- els for fine-grained visual recognition. ICCV, 2015. 1 tion. In ICCV, pages 321–328.  ...  Label- In CVPR Workshop on Fine-Grained Visual Categorization embedding for attribute-based classification. In CVPR, pages (FGVC), 2011. 1 819–826.  ... 
doi:10.1109/cvpr.2016.126 dblp:conf/cvpr/ZhangZLZ16 fatcat:aa5v7iwcwbaphhxkjrp2qypoje

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification [article]

Yongming Rao, Guangyi Chen, Jiwen Lu, Jie Zhou
2021 arXiv   pre-print
for fine-grained image recognition.  ...  Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks.  ...  Grant 61822603, Grant U1813218, and Grant U1713214, in part by a grant from the Beijing Academy of Artificial Intelligence (BAAI), and in part by a grant from the Institute for Guo Qiang, Tsinghua University  ... 
arXiv:2108.08728v2 fatcat:5imvpqpxcjbbxj5fbcotmbmnjy

Fused one-vs-all mid-level features for fine-grained visual categorization

Xiaopeng Zhang, Hongkai Xiong, Wengang Zhou, Qi Tian
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
To address the problems above, we propose a new framework for fine-grained visual categorization.  ...  As an emerging research topic, fine-grained visual categorization has been attracting growing attentions in recent years.  ...  results for fine-grained visual categorization so far.  ... 
doi:10.1145/2647868.2654937 dblp:conf/mm/0001XZT14 fatcat:v5dv6vlnbvezpatcws43z6nlq4

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization [article]

Jun Wang, Xiaohan Yu, Yongsheng Gao
2022 arXiv   pre-print
The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features.  ...  Theself-attention mechanism aggregates and weights the information from all patches to the classification token, making it perfectly suitable for FGVC.  ...  This work extends the ViT to both the large-scale FGVC and small-scale ultra-fine-grained-visual-categorization settings.  ... 
arXiv:2107.02341v3 fatcat:gtshz72mpbgqxhnaeeuat6cvcq

Mine the fine: Fine-grained fragment discovery

M. Hadi Kiapour, Wei Di, Vignesh Jagadeesh, Robinson Piramuthu
2015 2015 IEEE International Conference on Image Processing (ICIP)  
Moreover, our approach takes advantage of deep networks that are targeted towards fine-grained classification.  ...  for each category.  ...  fine-grained classification.  ... 
doi:10.1109/icip.2015.7351466 dblp:conf/icip/KiapourDJP15 fatcat:ihkvonpsxna6zbp4jz4zy6eveu

A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle Classification [article]

Krassimir Valev, Arne Schumann, Lars Sommer, Jürgen Beyerer
2018 arXiv   pre-print
task of fine-grained classification of vehicles.  ...  Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle.  ...  Such details are often crucial for successful fine-grained visual classification.  ... 
arXiv:1806.02987v1 fatcat:eqqt2fvq5zfffcybigm2mjxyqy

FenceMask: A Data Augmentation Approach for Pre-extracted Image Features [article]

Pu Li, Xiangyang Li, Xiang Long
2020 arXiv   pre-print
Our method achieved significant performance improvement on Fine-Grained Visual Categorization task and VisDrone dataset.  ...  We tested it on CIFAR10, CIFAR100 and ImageNet datasets for Coarse-grained classification, COCO2017 and VisDrone datasets for detection, Oxford Flowers, Cornel Leaf and Stanford Dogs datasets for Fine-Grained  ...  variety of computer vision tasks and demonstrated that our method has comparable performance on common datasets with current data enhancement methods, and particularly verified superior performance in fine-grained  ... 
arXiv:2006.07877v1 fatcat:luwi7gc56vaapapuna4oqiucbi

Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition

Tianshui Chen, Liang Lin, Riquan Chen, Yang Wu, Xiaonan Luo
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
For example, to achieve fine-grained image recognition (e.g., categorizing hundreds of subordinate categories of birds) usually requires a comprehensive visual concept organization including category labels  ...  of fine-grained image recognition.  ...  For example, to achieve fine-grained image recognition (e.g., categorizing hundreds of subordinate categories of birds) usually requires a comprehensive visual concept organization including category labels  ... 
doi:10.24963/ijcai.2018/87 dblp:conf/ijcai/ChenLCWL18 fatcat:iek67dt6mzftld5cll247t6mfa

Learning Category-Specific Dictionary and Shared Dictionary for Fine-Grained Image Categorization

Shenghua Gao, Ivor Wai-Hung Tsang, Yi Ma
2014 IEEE Transactions on Image Processing  
This paper targets fine-grained image categorization by learning a category-specific dictionary for each category and a shared dictionary for all the categories.  ...  Our proposed dictionary learning formulation not only applies to fine-grained classification, but also improves conventional basic-level object categorization and other tasks such as event recognition.  ...  This is the first work to use incoherence to improve the performance of fine-grained classification method, and we show the incoherence does improve the performance a lot for fine-grained image categorization  ... 
doi:10.1109/tip.2013.2290593 pmid:24239999 fatcat:rstuikkx7bfqbamve3iuzjigam

A Systematic Evaluation: Fine-Grained CNN vs. Traditional CNN Classifiers [article]

Saeed Anwar, Nick Barnes, Lars Petersson
2021 arXiv   pre-print
(ii) Do general CNN classifiers require any specific information to improve upon the fine-grained ones?  ...  Throughout this work, we train the general CNN classifiers without introducing any aspect that is specific to fine-grained datasets.  ...  Fine-Grain Classifiers Fine-grained visual classification is an important and well-studied problem.  ... 
arXiv:2003.11154v3 fatcat:bngglda6zfcpdepmzcqdpqrvxq
« Previous Showing results 1 — 15 out of 21,859 results