Dynamic sampling for deep metric learning
نویسندگان
چکیده
Deep metric learning maps visually similar images onto nearby locations and dissimilar apart from each other in an embedding manifold. The process is mainly based on the supplied image negative positive training pairs. In this paper, a dynamic sampling strategy proposed to organize pairs easy-to-hard order feed into network. It allows network learn general boundaries between categories easy at its early stages finalize details of model relying hard samples later. Compared existing sample mining approaches, are mined with little harm learned model. This formulated as two simple terms that compatible various loss functions. Consistent performance boost observed when it integrated several popular functions fashion search fine-grained search.
منابع مشابه
Deep metric learning for multi-labelled radiographs
Many radiological studies can reveal the presence of several co-existing abnormalities, each one represented by a distinct visual pattern. In this article we address the problem of learning a distance metric for plain radiographs that captures a notion of “radiological similarity”: two chest radiographs are considered to be similar if they share similar abnormalities. Deep convolutional neural ...
متن کاملFast Metric Learning For Deep Neural Networks
Similarity metrics are a core component of many information retrieval and machine learning systems. In this work we propose a method capable of learning a similarity metric from data equipped with a binary relation. By considering only the similarity constraints, and initially ignoring the features, we are able to learn target vectors for each instance using one of several appropriately designe...
متن کاملDiscriminative Metric Learning with Deep Forest
A Discriminative Deep Forest (DisDF) as a metric learning algorithm is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. The case of the fully supervised learning is studied when the class labels of individual training examples are known. The main idea underlying the algorithm is to assign weights to decisio...
متن کاملDeep Metric Learning Using Triplet Network
Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ran...
متن کاملSemi-supervised deep learning by metric embedding
Deep networks are successfully used as classification models yielding state-ofthe-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of their tendency to overfit easily when trained on small amounts of data. In this work we will explore a new training objective that is targeting a semi-supervise...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Pattern Recognition Letters
سال: 2021
ISSN: ['1872-7344', '0167-8655']
DOI: https://doi.org/10.1016/j.patrec.2021.06.027