Karaman, Kaan
Gundogdu, Erhan
Koc, Aykut
Alatan, Abdullah Aydın
Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep embedding learning by using a multi-task learning framework, in which the hierarchical labels (coarse and fine labels) of the samples are utilized both for classification and a quadruplet-based loss function. In order to improve the recognition strength of the learned features, we present a novel feature selection method specifically designed for four training samples of a quadruplet. By experiments, it is observed that the selection of very hard negative samples with relatively easy positive ones from the same coarse and fine classes significantly increases some performance metrics in a fine-grained dataset when compared to selecting the quadruplet samples randomly. The feature embedding learned by the proposed method achieves favorable performance against its state-of-the-art counterparts.


Multisource region attention network for fine-grained object recognition in remote sensing imagery
Sümbül, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (Institute of Electrical and Electronics Engineers (IEEE), 2019-07)
Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related subcategories. Multisource data analysis that aims to leverage the complementary spectral, spatial, and structural information embedded in different sources is a promising direction toward solving the fine-grained recognition problem that involves low between-class variance, small training set sizes for rare classes, and class imbalance. However, the common assumption of coregistered ...
Weakly supervised instance attention for multisource fine-grained object recognition with an application to tree species classification
Aygunes, Bulut; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2021-06-01)
Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories. However, for multisource tasks that involve relatively small objects, even the smallest registration errors can introduce high uncertainty in the classification process. We approach this problem from a weakly supervised learning perspective in which the input images correspond to larger neighborh...
Deep Distance Metric Learning For Maritime Vessel Identification
Gundogdu, Erhan; Solmaz, Berkan; Koç, Aykut; Yucesoy, Veysel; Alatan, Abdullah Aydın (2017-05-18)
This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. In order to increase the performance of visual vessel identification, we propose a joint learning framework which considers a classification and a distance metric learning cost function. The proposed method utilizes the quadruplet samples from a diverse image dataset t...
Multiple Access Communications for Age Minimization in UAV Aided Data Collection
Ogutcu, Oktay; Yüksel Turgut, Ayşe Melda (2022-01-01)
Data collection with unmanned aerial vehicles (UAVs) is a novel technology with many practical applications. In this paper, UAV aided data collection in sensor networks for time-critical applications is considered. Maximum age of information (AoI) is used as the performance metric, where both communication time and flight time contribute to AoI. Given that sensors form groups of two, the UAV aims to visit each line segment formed by the two sensors in each group once and to return to the data center. To min...
An algorithm for multiscale license plate detection and rule-based character segmentation
Karalı, Ali Onur; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2011)
License plate recognition (LPR) technology has great importance for the development of Intelligent Transportation Systems by automatically identifying the vehicles using image processing and pattern recognition techniques. Conventional LPR systems consist of license plate detection (LPD), character segmentation (CS) and character recognition (CR) steps. Successful detection of license plate and character locations have vital role for proper LPR. Most LPD and CS techniques in the literature assume fixed dist...
Citation Formats
K. Karaman, E. Gundogdu, A. Koc, and A. A. Alatan, “QUADRUPLET SELECTION METHODS FOR DEEP EMBEDDING LEARNING,” 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43119.