Browsing by Subject "Triplet loss"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Open Access Deep clustering via center-oriented margin free-triplet loss for skin lesion detection in highly ımbalanced datasets(Institute of Electrical and Electronics Engineers Inc., 2022-06-29) Öztürk, Şaban; Çukur, TolgaMelanoma is a fatal skin cancer that is curable and has dramatically increasing survival rate when diagnosed at early stages. Learning-based methods hold significant promise for the detection of melanoma from dermoscopic images. However, since melanoma is a rare disease, existing databases of skin lesions predominantly contain highly imbalanced numbers of benign versus malignant samples. In turn, this imbalance introduces substantial bias in classification models due to the statistical dominance of the majority class. To address this issue, we introduce a deep clustering approach based on the latent-space embedding of dermoscopic images. Clustering is achieved using a novel center-oriented margin-free triplet loss (COM-Triplet) enforced on image embeddings from a convolutional neural network backbone. The proposed method aims to form maximally-separated cluster centers as opposed to minimizing classification error, so it is less sensitive to class imbalance. To avoid the need for labeled data, we further propose to implement COM-Triplet based on pseudo-labels generated by a Gaussian mixture model (GMM). Comprehensive experiments show that deep clustering with COM-Triplet loss outperforms clustering with triplet loss, and competing classifiers in both supervised and unsupervised settings. © 2013 IEEE.Item Open Access Learning visual similarity for image retrieval with global descriptors and capsule networks(Springer, 2023-07-31) Durmuş, Duygu; Güdükbay, Uğur; Ulusoy, ÖzgürFinding matching images across large and unstructured datasets is vital in many computer vision applications. With the emergence of deep learning-based solutions, various visual tasks, such as image retrieval, have been successfully addressed. Learning visual similarity is crucial for image matching and retrieval tasks. Capsule Networks enable learning richer information that describes the object without losing the essential spatial relationship between the object and its parts. Besides, global descriptors are widely used for representing images. We propose a framework that combines the power of global descriptors and Capsule Networks by benefiting from the information of multiple views of images to enhance the image retrieval performance. The Spatial Grouping Enhance strategy, which enhances sub-features parallelly, and self-attention layers, which explore global dependencies within internal representations of images, are utilized to empower the image representations. The approach captures resemblances between similar images and differences between non-similar images using triplet loss and cost-sensitive regularized cross-entropy loss. The results are superior to the state-of-the-art approaches for the Stanford Online Products Database with Recall@K of 85.0, 94.4, 97.8, and 99.3, where K is 1, 10, 100, and 1000, respectively.Item Open Access Learning visual similarity for image retrieval with global descriptors and capsule networks(Bilkent University, 2021-07) Durmuş, DuyguFinding matching images across large and unstructured datasets plays an im-portant role in many computer vision applications. With the emergence of deep learning-based solutions, various visual tasks such as image retrieval have been successfully addressed. Learning visual similarity is crucial for image matching and retrieval tasks. An alternative deep learning architecture, named capsule networks, enables learning richer information that describes the object without losing the essential spatial relationship between the object and its parts. Besides, global descriptors are widely used for representing images. The proposed architecture combines the power of global descriptors and revised capsule networks to enhance image retrieval performance. It benefits from multi-ple views of object images and highlights the spatial relationship between objects and their parts. Spatial Grouping Enhance strategy, which enhances sub-features parallelly, and self-attention layers, which explore global dependencies within in-ternal representations of images, are utilized to empower the image representa-tions. The approach captures resemblances between similar images and di˙er-ences between the non-similar images using both triplet loss and cost-sensitive regularized cross-entropy loss instead of learning classification for individual im-ages. Based on the experiments, the results are superior to the state-of-the-art approaches for Stanford Online Products.