Filters








15,177 Hits in 5.1 sec

Iterative Object and Part Transfer for Fine-Grained Recognition [article]

Zhiqiang Shen and Yu-Gang Jiang and Dequan Wang and Xiangyang Xue
2017 arXiv   pre-print
Based on the located objects and parts, deep convolutional features are extracted for recognition.  ...  The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds.  ...  Acknowledgements This work was supported in part by two NSFC projects (#61572134 and #U1509206) and one grant from STCSM, China (#16QA1400500).  ... 
arXiv:1703.09983v1 fatcat:ceaivwvporguzfugj2wwqcgfqa

Picking Deep Filter Responses for Fine-Grained Image Recognition

Xiaopeng Zhang, Hongkai Xiong, Wengang Zhou, Weiyao Lin, Qi Tian
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.  ...  This paper proposes an automatic finegrained recognition approach which is free of any object / part annotation at both training and testing stages.  ...  Hence localizing and describing object and the corresponding parts become crucial for fine-grained recognition.  ... 
doi:10.1109/cvpr.2016.128 dblp:conf/cvpr/ZhangXZLT16 fatcat:uaxknyseknfljdm2dnhlzjw6bq

What makes ImageNet good for transfer learning? [article]

Minyoung Huh, Pulkit Agrawal, Alexei A. Efros
2016 arXiv   pre-print
Does adding more object classes improve performance? For the same data budget, how should the data be split into classes? Is fine-grained recognition necessary for learning good features?  ...  To answer these and related questions, we pre-trained CNN features on various subsets of the ImageNet dataset and evaluated transfer performance on PASCAL detection, PASCAL action classification, and SUN  ...  We gratefully acknowledge NVIDIA corporation for the donation of K40 GPUs and access to the NVIDIA PSG cluster for this research.  ... 
arXiv:1608.08614v2 fatcat:tnfvfyql2zhz3daxsyjmvto2km

Fine-Grained Recognition of Surface Targets with Limited Data

Runze Guo, Bei Sun, Xiaotian Qiu, Shaojing Su, Zhen Zuo, Peng Wu
2020 Electronics  
In this paper, we introduce a multi-attention residual model based on deep learning methods, in which channel and spatial attention modules are applied for feature fusion.  ...  Recognition of surface targets has a vital influence on the development of military and civilian applications such as maritime rescue patrols, illegal-vessel screening, and maritime operation monitoring  ...  The experimental results show that our model is not only stable for general object recognition, but also better for objects with small visual differences than commonly used fine-grained classification  ... 
doi:10.3390/electronics9122044 fatcat:aw32wtrnhvcmnkzbidn6iltjlq

Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition [article]

Hao Li, Xiaopeng Zhang, Hongkai Xiong, Qi Tian
2020 arXiv   pre-print
The principle lies in that attribute features are shared among fine-grained sub-categories, and can be seamlessly transferred among images.  ...  Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up.  ...  Fine-grained Recognition Fine-grained recognition has been studied for several years.  ... 
arXiv:2004.02684v2 fatcat:vususbkgpvcc7ebm3gwqa5bm6u

Multi-stream aggregation network for fine-grained crop pests and diseases image recognition

Xuebo Jin, Zhi Tao, Jianlei Kong
2021 International Journal of Cybernetics and Cyber-Physical Systems  
with models transferred named as MSA-NET (Multi-Stream Aggregation Network) for fine-grained species recognition based on fusion idea.  ...  The MSA-NET model achieves competitive results in fine-grained pests and disease recognition outperforming state-of-the-art methods.  ...  for the fine-grained classification and object localisation.  ... 
doi:10.1504/ijccps.2021.113105 fatcat:ajbg3nrmejejrnac4puigcuzfq

Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery

Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy
2018 IEEE Transactions on Geoscience and Remote Sensing  
Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image  ...  Then, we show how knowledge transfer can be performed for the unseen classes by maximizing this function during inference.  ...  CONCLUSION We studied the ZSL problem for fine-grained object recognition in remotely sensed images.  ... 
doi:10.1109/tgrs.2017.2754648 fatcat:cgjm42zdovcbnc57cjt7rki4dm

CoCoNet: A Collaborative Convolutional Network [article]

Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal
2020 arXiv   pre-print
We also introduce a new public dataset for fine-grained species recognition, that of Indian endemic birds and have reported initial results on it.  ...  This gives CoCoNet more power to encode the fine-grained nature of the data with limited samples. We perform a detailed study of the performance with 1-stage and 2-stage transfer learning.  ...  ImageNet) for the task of base object recognition. The network is then fine-tuned on the smaller target dataset for fine-grained recognition.  ... 
arXiv:1901.09886v4 fatcat:xxc72ackb5epxfwh6w3xbaprga

Exemplar-Specific Patch Features for Fine-Grained Recognition [chapter]

Alexander Freytag, Erik Rodner, Trevor Darrell, Joachim Denzler
2014 Lecture Notes in Computer Science  
We evaluate our approach for fine-grained recognition on the CUB-2011 birds dataset and show that high recognition rates can be obtained by model combination.  ...  In this paper, we present a new approach for fine-grained recognition or subordinate categorization, tasks where an algorithm needs to reliably differentiate between visually similar categories, e.g.,  ...  Experiments We evaluate our approach for fine-grained recognition on the CUB-2011 dataset [28] and use the provided split for training and testing.  ... 
doi:10.1007/978-3-319-11752-2_12 fatcat:sjqj7a3khbgjfnxmbzup4rbsry

Fine-Grained Image Analysis with Deep Learning: A Survey [article]

Xiu-Shen Wei and Yi-Zhe Song and Oisin Mac Aodha and Jianxin Wu and Yuxin Peng and Jinhui Tang and Jian Yang and Serge Belongie
2021 arXiv   pre-print
image recognition and fine-grained image retrieval.  ...  Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.  ...  ACKNOWLEDGMENTS The authors would like to thank the editor and the anonymous reviewers for their constructive comments.  ... 
arXiv:2111.06119v2 fatcat:ninawxsjtnf4lndtqquuwl3weq

Cold Start Problem of Vehicle Model Recognition under Cross-Scenario Based on Transfer Learning

Hongbo Wang, Qian Xue, Tong Cui, Yangyang Li, Huacheng Zeng
2020 Computers Materials & Continua  
Through experiments, transfer the vehicle model recognition from the network image dataset (source domain) to the surveillance-nature dataset (target domain), both Top-1 and Top-5 accuracy have been improved  ...  However, if you don't have a lot of vehicle model datasets for the current scene, you cannot properly train a model.  ...  Similar to the fine-tune part, we set the parameters of the source and target domains with a batch-size of 128 for two AlexNet experiments. The number of training iterations is still 60,000.  ... 
doi:10.32604/cmc.2020.07290 fatcat:go6faikmpbfj3hmkpbbcwk22pm

Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition [article]

Heliang Zheng, Jianlong Fu, Zheng-Jun Zha, Jiebo Luo
2019 arXiv   pre-print
., beak and eyes for a bird) plays a significant role in fine-grained image recognition.  ...  Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost.  ...  The soft target cross entropy aims to distill the learned feature for fine-grained details and transfer such information to the master-net.  ... 
arXiv:1903.06150v2 fatcat:5nfti7jptzhnllvq3uudh7x5aa

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

Shaoli Huang, Zhe Xu,Dacheng Tao,Ya Zhang
2015 arXiv   pre-print
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.  ...  object-level and part-level cues simultaneously.  ...  The object stream utilizes boundingbox-level supervision to capture object-level semantics for fine-grained recognition.  ... 
arXiv:1512.08086v1 fatcat:f5n6un6jw5gznjqcrrsctjzxhi

Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition [article]

Luming Tang, Davis Wertheimer, Bharath Hariharan
2020 arXiv   pre-print
While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification.  ...  Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone.  ...  Left: The fine-grained few-shot recognition task. Objects share the same part structure and differences between categories are subtle.  ... 
arXiv:2004.00705v1 fatcat:nczpq6ffvbggpkewy3o3ckamt4

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)  
object-level and part-level cues simultaneously.  ...  In this paper, we propose a novel Part-Stacked CNN architecture that explicitly explains the finegrained recognition process by modeling subtle differences from object parts.  ...  , NSFC 61221001, STCSM 12DZ2272600, and the 111 Project B07022.  ... 
doi:10.1109/cvpr.2016.132 dblp:conf/cvpr/HuangXTZ16 fatcat:bc2zb23bpzbhrf3wq47r5mtlha
« Previous Showing results 1 — 15 out of 15,177 results