1,720,974 research outputs found
EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task
No full textFine-Grained classification models can expressly focus on the relevant details useful to distinguish highly similar classes typically when the intra-class variance is high and the inter-class variance is low given a dataset. Most of these models use part annotations as bounding box, location part, text attributes to enhance the performance of classification and other models use sophisticated techniques to extract an attention map automatically. We assume that part-based approaches as the automatic cropping method suffers from a missing representation of local features, which are fundamental to distinguish similar objects. While Fine-Grained classification endeavours to recognize the leaf of a graph, humans recognize an object trying also to make a semantic association. In this paper, we use the semantic association structured as a hierarchy (taxonomy) as supervised signals and used them in an end-to-end deep neural network model termed as EnGraf-Net. Extensive experiments on three well-known datasets: Cifar-100, CUB-200-2011 and FGVC-Aircraft prove the superiority of EnGraf-Net over many Fine-Grained models and it is competitive with the most recent best models without using any cropping technique or manual annotations
Is one teacher model enough to transfer knowledge to a student model?
No full textNowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance. In this paper, we designed a transfer learning methodology that combines the learned features of different teachers to a student network in an end-to-end model, improving the performance of the student network in classification tasks over different datasets. In addition to this, we tried to answer the following questions which are in any case directly related to the transfer learning problem addressed here. Is it possible to improve the performance of a small neural network by using the knowledge gained from a more powerful neural network? Can a deep neural network outperform the teacher using transfer learning? Experimental results suggest that neural networks can transfer their learning to student networks using our proposed architecture, designed to bring to light a new interesting approach for transfer learning techniques. Finally, we provide details of the code and the experimental settings
Dynamic Decision Boundary for One-class Classifiers applied to non-uniformly Sampled Data
No full textA typical issue in Pattern Recognition is the nonuniformly sampled data, which modifies the general performance and capability of machine learning algorithms to make accurate predictions. Generally, the data is considered non-uniformly sampled when in a specific area of data space, they are not enough, leading us to misclassification problems. This issue cut down the goal of the one-class classifiers decreasing their performance. In this paper, we propose a one-class classifier based on the minimum spanning tree with a dynamic decision boundary (OCdmst) to make good prediction also in the case we have non-uniformly sampled data. To prove the effectiveness and robustness of our approach we compare with the most recent one-class classifier reaching the state-of-the-art in most of them. The code and all results are available online https://gitlab.com/artelabsuper/ocdmst
OCmst: One-class novelty detection using convolutional neural network and minimum spanning trees
No full textWe present a novel model called One Class Minimum Spanning Tree (OCmst) for novelty detection problem that uses a Convolutional Neural Network (CNN) as deep feature extractor and graph-based model based on Minimum Spanning Tree (MST). In a novelty detection scenario, the training data is no polluted by outliers (abnormal class) and the goal is to recognize if a test instance belongs to the normal class or the abnormal class. Our approach uses the deep features from CNN to feed a pair of MSTs built starting from each test instance. To cut down the computational time we use a parameter γ to specify the size of the MST's starting to the neighbours from the test instance. To prove the effectiveness of the proposed approach we conducted experiments on two publicly available datasets, well-known in literature and we achieved the state-of-the-art results on the CIFAR10 dataset
Learn class hierarchy using convolutional neural networks
No full textA large amount of research on Convolutional Neural Networks (CNN) has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as hierarchical classification problems, in which the classes to be predicted are organized in a hierarchy of classes. In this paper, we propose a new architecture for hierarchical classification, introducing a stack of deep linear layers using cross-entropy loss functions combined to a center loss function. The proposed architecture can extend any neural network model and simultaneously optimizes loss functions to discover local hierarchical class relationships and a loss function to discover global information from the whole class hierarchy while penalizing class hierarchy violations. We experimentally show that our hierarchical classifier presents advantages to the traditional classification approaches finding application in computer vision tasks. The same approach can also be applied to some CNN for text classification
Visual Word Embedding for Text Classification
No full textThe question we answer with this paper is: ‘can we convert a text document into an image to take advantage of image neural models to classify text documents?’ To answer this question we present a novel text classification method that converts a document into an encoded image, using word embedding. The proposed approach computes the Word2Vec word embedding of a text document, quantizes the embedding, and arranges it into a 2D visual representation, as an RGB image. Finally, visual embedding is categorized with state-of-the-art image classification models. We achieved competitive performance on well-known benchmark text classification datasets. In addition, we evaluated our proposed approach in a multimodal setting that allows text and image information in the same feature space
Sentinel 2 time series analysis with 3d feature pyramid network and time domain class activation intervals for crop mapping
No full textIn this paper, we provide an innovative contribution in the research domain dedicated to crop mapping by exploiting the of Sentinel-2 satellite images time series, with the specific aim to extract information on “where and when” crops are grown. The final goal is to set up a workflow able to reliably identify (classify) the different crops that are grown in a given area by exploiting an end-to-end (3+2)D convolutional neural network (CNN) for semantic segmentation. The method also has the ambition to provide information, at pixel level, regarding the period in which a given crop is cultivated during the season. To this end, we propose a solution called Class Activation Interval (CAI) which allows us to interpret, for each pixel, the reasoning made by CNN in the classification determining in which time interval, of the input time series, the class is likely to be present or not. Our experiments, using a public domain dataset, show that the approach is able to accurately detect crop classes with an overall accuracy of about 93% and that the network can detect discriminatory time intervals in which crop is cultivated. These results have twofold importance: (i) demonstrate the ability of the network to correctly interpret the investigated physical process (i.e., bare soil condition, plant growth, senescence and harvesting according to specific cultivated variety) and (ii) provide further information to the end-user (e.g., the presence of crops and its temporal dynamics)
Combining Optimization Methods Using an Adaptive Meta Optimizer
No full textOptimization methods are of great importance for the efficient training of neural networks. There are many articles in the literature that propose particular variants of existing optimizers. In our article, we propose the use of the combination of two very different optimizers that, when used simultaneously, can exceed the performance of the single optimizers in very different problems. We propose a new optimizer called ATMO (AdapTive Meta Optimizers), which integrates two different optimizers simultaneously weighing the contributions of both. Rather than trying to improve each single one, we leverage both at the same time, as a meta-optimizer, by taking the best of both. We have conducted several experiments on the classification of images and text documents, using various types of deep neural models, and we have demonstrated through experiments that the proposed ATMO produces better performance than the single optimizers
Learning to Navigate in the Gaussian Mixture Surface
No full textIn the last years, deep learning models have achieved remarkable generalization capability on computer vision tasks, obtaining excellent results in fine-grained classification problems. Sophisticated approaches based-on discriminative feature learning via patches have been proposed in the literature, boosting the model performances and achieving the state-of-the-art over well-known datasets. Cross-Entropy (CE) loss function is commonly used to enhance the discriminative power of the deep learned features, encouraging the separability between the classes. However, observing the activation map generated by these models in the hidden layer, we realize that many image regions with low discriminative content have a high activation response and this could lead to misclassifications. To address this problem, we propose a loss function called Gaussian Mixture Centers (GMC) loss, leveraging on the idea that data follow multiple unimodal distributions. We aim to reduce variances considering many centers per class, using the information from the hidden layers of a deep model, and decreasing the high response from the unnecessary areas of images detected along the baselines. Using jointly CE and GMC loss, we improve the learning generalization model overcoming the performance of the baselines in several use cases. We show the effectiveness of our approach by carrying out experiments over CUB-200-2011, FGVC-Aircraft, Stanford-Dogs benchmarks, and considering the most recent Convolutional Neural Network (CNN)
- …
