Tranfer Learning in Large Scale Datasets
نویسندگان
چکیده
Conventional image classification techniques aim to predict class labels by training a classifier with the provided training labels, but the internal relationship between classes has been ignored. In this project, we explore the feasibility of transferring knowledge between classes to help boost up the classification accuracy. Two transfer learning approaches have been studied, namely, instance transfer by jointly optimizing classifiers via grouping source and target training examples, and parameter transfer by exploring the relationship between classifier parameters. We demonstrate the parameter transfer scheme achieves a remarkably better performance compared to conventional image classification techniques and the relatively simple instance transfer approach.
منابع مشابه
A Pre-Trained Ensemble Model for Breast Cancer Grade Detection Based on Small Datasets
Background and Purpose: Nowadays, breast cancer is reported as one of the most common cancers amongst women. Early detection of the cancer type is essential to aid in informing subsequent treatments. The newest proposed breast cancer detectors are based on deep learning. Most of these works focus on large-datasets and are not developed for small datasets. Although the large datasets might lead ...
متن کاملLarge Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (FGVC) tasks (e.g., recognizing bird species or car make & model). In such scenarios, data annotation often calls for specialized domain knowledge and thus is difficult to scale. In this work, we first tackle a problem ...
متن کاملIntegrating memetic search into the BioHEL evolutionary learning system for large-scale datasets
Local search methods are widely used to improve the performance of evolutionary computation algorithms in all kinds of domains. Employing advanced and efficient exploration mechanisms becomes crucial in complex and very large (in terms of search space) problems, such as when employing evolutionary algorithms to large-scale data mining tasks. Recently, the GAssist Pittsburgh evolutionary learnin...
متن کاملGraph-based semi-supervised learning with multi-modality propagation for large-scale image datasets
Semi-supervised learning (SSL) is widely-used to explore the vast amount of unlabeled data in the world. Over the decade, graph-based SSL becomes popular in automatic image annotation due to its power of learning globally based on local similarity. However, recent studies have shown that the emergence of large-scale datasets challenges the traditional methods. On the other hand, most previous w...
متن کاملLarge-scale Datasets: Faces with Partial Occlusions and Pose Variations in the Wild
Face detection methods have relied on face datasets for training. However, existing face datasets tend to be in small scales for face learning in both constrained and unconstrained environments. In this paper, we first introduce our large-scale image datasets, Large-scale Labeled Face (LSLF) and noisy Large-scale Labeled Non-face (LSLNF). Our LSLF dataset consists of a large number of unconstra...
متن کامل