datamining is discovering interesting knowledge, namely associations, patterns, changes, significant structures, and anomalies, from enormous quantities of data stored in data warehouses, databases, or other data rep...
详细信息
Automated machinelearning (AutoML) creates additional opportunities for less advanced users to build and test their own datamining models. Even though AutoML creates the models for the user, there is still technical...
详细信息
Digit recognition is essential for interpreting image processing and patternrecognition since a machine cannot classify handwritten digits. Many real-time applications include OCR (Optical Character recognition), whi...
详细信息
Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models fruga...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on large collections of labeled data. Among the existing solutions, deep active learning is currently witnessing a major interest and its purpose is to train deep networks using as few labeled samples as possible. However, the success of active learning is highly dependent on how critical are these samples when training models. In this paper, we devise a novel active learning approach for label-efficient training. the proposed method is iterative and aims at minimizing a constrained objective function that mixes diversity, representativity and uncertainty criteria. the proposed approach is probabilistic and unifies all these criteria in a single objective function whose solution models the probability of relevance of samples (i.e., how critical) when learning a decision function. We also introduce a novel weighting mechanism based on reinforcement learning, which adaptively balances these criteria at each training iteration, using a particular stateless Q-learning model. Extensive experiments conducted on staple image classification data, including Object-DOTA, show the effectiveness of our proposed model w.r.t. several baselines including random, uncertainty and flat as well as other work.
When confronted with recognizing large facial images, traditional feature extraction methods encounter significant difficulties in extracting compelling features, leading to low accuracy in face recognition. this pape...
详细信息
Domain Generalization (DG) in Person Re-identification (ReID) tackles the task of testing in unseen domains without using target domain data during training. Existing DG ReID methods achieve impressive performance wit...
详细信息
ISBN:
(纸本)9789819985548;9789819985555
Domain Generalization (DG) in Person Re-identification (ReID) tackles the task of testing in unseen domains without using target domain data during training. Existing DG ReID methods achieve impressive performance with unified ensemble models or multi-expert hybrid networks. However, as the number of source domains increases, complex relationships between training samples result in domain-invariant characteristics with spurious correlations, impacting further generalization. To address this, we propose a Bilateral Frequency-Aware Network(BFAN) that leverages spectral feature correlation learning for discriminative hybrid features. BFAN includes a Bilateral Frequency Component-guided Attention (BFCA) module to capture semantic information from diverse frequency features and fuse it with spatial features. Additionally, a Fourier Noise Masquerade Filtering (FNMF) module is introduced to suppress non-generalization-supporting components in the frequency domain. Extensive experiments on various datasets demonstrate our method's notably competitive performance.
Since the integration of smart grids in power grid sector, large amounts of high frequency load consumption data gets accumulated at the microgrids which has been utilized for study and analysis. the rich data availab...
详细信息
ISBN:
(纸本)9783031451690;9783031451706
Since the integration of smart grids in power grid sector, large amounts of high frequency load consumption data gets accumulated at the microgrids which has been utilized for study and analysis. the rich data availability allows load forecasts from lower level, at buildings to aggregate levels. the aggregate level forecasts have recently gained importance because it acts as a dimensionality reduction approach, however as a result of the reduction, the information content is reduced too. the deep learning models have the capacity to extract the useful information from datasets, hence this paper aims to bring forward the performance of the deep models in case of multiple aggregation techniques. A comparative analysis is performed on the different aggregation techniques and the best is reported.
the quantization algorithm compresses the original network by reducing the numerical bit width of the model and improves the calculation speed. However, it is difficult to determine the optimal bit width of the networ...
详细信息
Underwater acoustic target recognition (UATR) is one of the essential research directions in the underwater acoustic signal processing field. the machinelearning-based recognition methods have solved some performance...
详细信息
Face masks became a necessity since the outbreak of COVID-19 as a way to avoid the spread, especially in crowded places, and are counted as one of the most effective methods to control the spread. However, some people...
详细信息
暂无评论