WEAKLY SUPERVISED DEEP CONVOLUTIONAL NETWORKS FOR FINE-GRAINED OBJECT RECOGNITION IN MULTISPECTRAL IMAGES

Download
2019-01-01
Aygunes, Bulut
AKSOY, SELİM
Cinbiş, Ramazan Gökberk
The challenging task of training object detectors for fine-grained classification faces additional difficulties when there are registration errors between the image data and the ground truth. We propose a weakly supervised learning methodology for the classification of 40 types of trees by using fixed-sized multispectral images with a class label but with no exact knowledge of the object location. Our approach consists of an end-to-end trainable convolutional neural network with separate branches for learning class-specific and location-specific scoring of image regions. Comparative experiments show that the proposed method simultaneously learns to detect and classify the objects of interest with high accuracy.
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Suggestions

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...
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
Cinbiş, Ramazan Gökberk; Schmid, Cordelia (2017-01-01)
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the obj...
A Fast shape detection approach by directional integrations
Okman, Osman Erman; Akar, Gözde; Department of Electrical and Electronics Engineering (2013)
Detection and identification of objects from aerial images are important problems for various types of application areas. For many of the man-made structures shape is a fundamental feature by which these objects are separated from the background and other structures. In this thesis, a novel geometric shape detection algorithm based on the spatial properties of structures is proposed. Since the objects are transformed into 1-D vectors by evaluating directional integrals and detections occur by the analysis o...
Representation Learning for Contextual Object and Region Detection in Remote Sensing
Firat, Orhan; Can, Gulcan; Yarman Vural, Fatoş Tunay (2014-08-28)
The performance of object recognition and classification on remote sensing imagery is highly dependent on the quality of extracted features, amount of labelled data and the priors defined for contextual models. In this study, we examine the representation learning opportunities for remote sensing. First we attacked localization of contextual cues for complex object detection using disentangling factors learnt from a small amount of labelled data. The complex object, which consists of several sub-parts is fu...
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Sumbul, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2018-02-01)
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 data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists f...
Citation Formats
B. Aygunes, S. AKSOY, and R. G. Cinbiş, “WEAKLY SUPERVISED DEEP CONVOLUTIONAL NETWORKS FOR FINE-GRAINED OBJECT RECOGNITION IN MULTISPECTRAL IMAGES,” presented at the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, JAPAN, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/39730.