Filters








15,228 Hits in 10.5 sec

Multi-label learning by Image-to-Class distance for scene classification and image annotation

Zhengxiang Wang, Yiqun Hu, Liang-Tien Chia
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
In this paper, we propose a multi-label learning framework based on Imageto-Class (I2C) distance, which is recently shown useful for image classification.  ...  We adjust this I2C distance to cater for the multi-label problem by learning a weight attached to each local feature patch and formulating it into a large margin optimization problem.  ...  [23] developed a multi-instance multi-label (MIML) learning framework and applied it for scene classification.  ... 
doi:10.1145/1816041.1816060 dblp:conf/civr/WangHC10 fatcat:cpobbeyow5dflg27ii5taakzzq

A novel active learning technique for multi-label remote sensing image scene classification

Begüm Demir, Bayable Teshome Zegeye, Lorenzo Bruzzone, Francesca Bovolo, Jon Atli Benediktsson
2018 Image and Signal Processing for Remote Sensing XXIV  
This paper presents a novel multi-label active learning (MLAL) technique in the framework of multi-label remote sensing (RS) image scene classification problems.  ...  Unlike the standard AL methods, the proposed MLAL technique redefines active learning by evaluating the informativeness of each image based on its multiple land-cover classes.  ...  ACKNOWLEDGMENT This work was supported by the European Research Council under the ERC Starting Grant BigEarth-759764.  ... 
doi:10.1117/12.2500191 fatcat:sni47oldh5eyxjq2swjvhrzmm4

Weakly-Supervised Road Affordances Inference and Learning in Scenes without Traffic Signs [article]

Huifang Ma, Yue Wang, Rong Xiong, Sarath Kodagoda, Qianhui Luo
2019 arXiv   pre-print
The first step analyzes vehicle trajectories to get partial affordances annotation on image, and the second step implements a weakly-supervised network to learn partial annotation and predict complete  ...  center and remaining distance.  ...  Acknowledgements This work was supported in part by Science and Technology Project of Zhejiang Province (2019C01043) and in part by the National Nature Science Foundation of China (U1609210,61903332).  ... 
arXiv:1911.12007v1 fatcat:3q6jzlfcoje4leo3yqwtr23k3a

Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification [article]

Changsheng Li and Chong Liu and Lixin Duan and Peng Gao and Kai Zheng
2020 arXiv   pre-print
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem.  ...  To capture the relationships between image features and labels, we aim to learn a two-way deep distance metric over the embedding space from two different views, i.e., the distance between one image and  ...  Deep learning for multi-label image classification: Recently, deep learning has been gradually applied to multi-label image classification.  ... 
arXiv:2007.13547v1 fatcat:6slei7dv25ej5hcs5vqsztc7uq

Learning Contextual Metrics for Automatic Image Annotation [chapter]

Zuotao Liu, Xiangdong Zhou, Yu Xiang, Yan-Tao Zheng
2010 Lecture Notes in Computer Science  
In this work, we present a novel Contextual Metric Learning (CML) method for learning a set of contextual distance metrics for real world multi-label images.  ...  The semantic contextual information is shown to be an important resource for improving the scene and image recognition, but is seldom explored in the literature of previous distance metric learning (DML  ...  For the scene and image classification and semantic annotation problems, the task is to assign multiple labels to each vision instance, so called multi-label classification.  ... 
doi:10.1007/978-3-642-15702-8_12 fatcat:72iivm6sp5ctvksavecv6ckhsu

Distance transform regression for spatially-aware deep semantic segmentation

Nicolas Audebert, Alexandre Boulch, Bertrand Le Saux, Sébastien Lefèvre
2019 Computer Vision and Image Understanding  
After computing the distance transform on the label masks, we train a FCN in a multi-task setting in both discrete and continuous spaces by learning jointly classification and distance regression.  ...  Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks.  ...  Fig. 2 : 2 Multi-task learning framework by performing both distance regression and pixel-wise classification.  ... 
doi:10.1016/j.cviu.2019.102809 fatcat:3i4svm3cifcjxay5bpx3udrrou

Random Sampling Image to Class Distance for Photo Annotation

Deyuan Zhang, Bingquan Liu, Chengjie Sun, Xiaolong Wang
2010 Conference and Labs of the Evaluation Forum  
Image classification or annotation is proved difficult for the computer algorithms.  ...  In this paper, we extend the image to class distance which is more general, and use the random sampling technique to alleviate the situation of the imbalance of the training datasets.  ...  This investigation was supported by the project of the National Natural Science Foundation of China (grants No. 60973076), Special Fund Projects for Harbin Science and Technology Innovation Talents(grants  ... 
dblp:conf/clef/ZhangLSW10 fatcat:hyd5hs2xoffevngkuteedu7rle

Distance transform regression for spatially-aware deep semantic segmentation [article]

Nicolas Audebert, Alexandre Boulch, Bertrand Le Saux, Sébastien Lefèvre
2019 arXiv   pre-print
After computing the distance transform on the label masks, we train a FCN in a multi-task setting in both discrete and continuous spaces by learning jointly classification and distance regression.  ...  Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks.  ...  Fig. 2 : 2 Multi-task learning framework by performing both distance regression and pixel-wise classification.  ... 
arXiv:1909.01671v1 fatcat:4hfqxkflbjemld6c3csorvcvne

MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding [article]

Xiaoman Qi, PanPan Zhu, Yuebin Wang, Liqiang Zhang, Junhuan Peng, Mengfan Wu, Jialong Chen, Xudong Zhao, Ning Zang, P.Takis Mathiopoulos
2020 arXiv   pre-print
Few multi-label high spatial resolution remote sensing datasets have been developed to train deep learning models for multi-label based tasks, such as scene classification and image retrieval.  ...  To better understand scene images in the field of remote sensing, multi-label annotation of scene images is necessary.  ...  For these reasons, multi-label annotation of an image is necessary to present more details of the image and improve the performance of scene understanding.  ... 
arXiv:2010.00243v1 fatcat:fd5sa7ux3neddjuixnkyprt2wa

BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval [article]

Gencer Sumbul, Arne de Wall, Tristan Kreuziger, Filipe Marcelino, Hugo Costa, Pedro Benevides, Mário Caetano, Begüm Demir, Volker Markl
2021 arXiv   pre-print
In our experiments, we show the potential of BigEarthNet-MM for multi-modal multi-label image retrieval and classification problems by considering several state-of-the-art DL models.  ...  multi-label remote sensing (RS) image retrieval and classification.  ...  RS image scene classification systems aim at automatically assigning class labels to each RS image scene in a large archive [3] , [4] .  ... 
arXiv:2105.07921v1 fatcat:pptg5dlcrbdcvldbyfxkykxfju

Visually Exploring Multi-Purpose Audio Data [article]

David Heise, Helen L. Bear
2021 arXiv   pre-print
acoustic scene classification.  ...  We use the visual assessment of cluster tendency (VAT) technique on a well known data set to observe how the samples naturally cluster, and we make comparisons to the labels used for audio geotagging and  ...  This suggestion is supported by results in [2] where results showed that multi-task learning for jointly classifying scenes and cities achieved the greatest accuracy.  ... 
arXiv:2110.04584v1 fatcat:aa6apxylabdirmifi4luxttd4i

Graph Relation Network: Modeling Relations Between Scenes for Multilabel Remote-Sensing Image Classification and Retrieval

Jian Kang, Ruben Fernandez-Beltran, Danfeng Hong, Jocelyn Chanussot, Antonio Plaza
2020 IEEE Transactions on Geoscience and Remote Sensing  
Owing to the proliferation of large-scale remote sensing (RS) archives with multiple annotations, multi-label RS scene classification and retrieval are becoming increasingly popular.  ...  To fill this gap, we propose a new graph relation network (GRN) for multi-label RS scene categorization.  ...  ACKNOWLEDGMENT The authors would like to thank the authors for their efforts in creating the multi-label datasets based on UCM, AID and DFC15, and the reviewers for their valuable suggestions.  ... 
doi:10.1109/tgrs.2020.3016020 fatcat:qrjfmxi5vfe2hldfbu5hf5ytaq

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Yating Gu, Yantian Wang, Yansheng Li
2019 Applied Sciences  
RSISU includes the following sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection.  ...  Similar to other domains (e.g., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU.  ...  For multi-label problems, conventional RSISR systems usually perform single-label retrieval, which underestimates the complicacy of RS images, where an image may be labeled by several tags, thus leading  ... 
doi:10.3390/app9102110 fatcat:oj3acgbmwnhzppxvvjbsn5cfzq

PUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral images [article]

Anirban Santara, Jayeeta Datta, Sourav Sarkar, Ankur Garg, Kirti Padia, Pabitra Mitra
2019 arXiv   pre-print
However, the scarcity of labeled training examples and spatial variability of spectral signature are two of the biggest challenges faced by hyperspectral image classification.  ...  Given a hyperspectral scene, the user labels some positive samples of a material he/she is looking for and our goal is to retrieve all the remaining instances of the query material in the scene.  ...  We would also like to thank Kiryo et al [18] for sharing their code for the generic PU Learning framework.  ... 
arXiv:1904.04547v1 fatcat:4d33mzbulbfqlkk2kja2trzwj4

An Iterative Partitioning-Based Method for Semi-Supervised Annotation Learning in Image Collections

Rene Grzeszick, Gernot A. Fink
2016 International journal of pattern recognition and artificial intelligence  
Labeling images is tedious and costly work that is required for many applications, for example, tagging, grouping and exploring of image collections.  ...  It is therefore desirable to either reduce the human effort or infer additional knowledge by addressing this task with algorithms that allow for learning image annotations in a semi-supervised manner.  ...  However, for very diverse classification problems such as natural scene recognition the majority of samples are rather difficult to assign to a class, because of the high intra class variability and ambiguities  ... 
doi:10.1142/s0218001416550053 fatcat:7se2zlj4dzhhvjtqt342zbmzfm
« Previous Showing results 1 — 15 out of 15,228 results