This paper presents the analysis of the impact of a floating-point number precision reduction on the quality of text classification. The precision reduction of the vectors representing the data (e.g. TF-IDF representation in our case) allows for a decrease of computing time and memory footprint on dedicated hardware platforms. The impact of precision reduction on the classification quality was performed on 5 corpora, using 4 different classifiers. Also, dimensionality reduction was taken into account. Results indicate that the precision reduction improves classification accuracy for most cases (up to 25% of error reduction). In general, the reduction from 64 to 4 bits gives the best scores and ensures that the results will not be worse than with the full floating-point representation.
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.
Music tag words that describe music audio by text have different levels of abstraction. Taking this issue into account, we propose a music classification approach that aggregates multi-level and multi-scale features using pre-trained feature extractors. In particular, the feature extractors are trained in sample-level deep convolutional neural networks using raw waveforms. We show that this approach achieves state-of-the-art results on several music classification datasets.
Most of the traditional convolutional neural networks (CNNs) implements bottom-up approach (feed-forward) for image classifications. However, many scientific studies demonstrate that visual perception in primates rely on both bottom-up and top-down connections. Therefore, in this work, we propose a CNN network with feedback structure for Solar power plant detection on middle-resolution satellite images. To express the strength of the top-down connections, we introduce feedback CNN network (FB-Net) to a baseline CNN model used for solar power plant classification on multi-spectral satellite data. Moreover, we introduce a method to improve class activation mapping (CAM) to our FB-Net, which takes advantage of multi-channel pulse coupled neural network (m-PCNN) for weakly-supervised localization of the solar power plants from the features of proposed FB-Net. For the proposed FB-Net CAM with m-PCNN, experimental results demonstrated promising results on both solar-power plant image classification and detection task.
Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algorithms called deep neural networks (DNNs) that achieve human-level classification performance on object recognition tasks. Furthermore, a growing number of studies report similarities in the way DNNs and the human visual system process objects, suggesting that current DNNs may be good models of human visual object recognition. Yet there clearly exist important architectural and processing differences between state-of-the-art DNNs and the primate visual system. The potential behavioural consequences of these differences are not well understood. We aim to address this issue by comparing human and DNN generalisation abilities towards image degradations. We find the human visual system to be more robust to image manipulations like contrast reduction, additive noise or novel eidolon-distortions. In addition, we find progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker, indicating that there may still be marked differences in the way humans and current DNNs perform visual object recognition. We envision that our findings as well as our carefully measured and freely available behavioural datasets provide a new useful benchmark for the computer vision community to improve the robustness of DNNs and a motivation for neuroscientists to search for mechanisms in the brain that could facilitate this robustness.
This paper introduces a novel deep learning framework including a lexicon-based approach for sentence-level prediction of sentiment label distribution. We propose to first apply semantic rules and then use a Deep Convolutional Neural Network (DeepCNN) for character-level embeddings in order to increase information for word-level embedding. After that, a Bidirectional Long Short-Term Memory Network (Bi-LSTM) produces a sentence-wide feature representation from the word-level embedding. We evaluate our approach on three Twitter sentiment classification datasets. Experimental results show that our model can improve the classification accuracy of sentence-level sentiment analysis in Twitter social networking.
This study proposed an exhaustive stable/reproducible rule-mining algorithm combined to a classifier to generate both accurate and interpretable models. Our method first extracts rules (i.e., a conjunction of conditions about the values of a small number of input features) with our exhaustive rule-mining algorithm, then constructs a new feature space based on the most relevant rules called "local features" and finally, builds a local predictive model by training a standard classifier on the new local feature space. This local feature space is easy interpretable by providing a human-understandable explanation under the explicit form of rules. Furthermore, our local predictive approach is as powerful as global classical ones like logistic regression (LR), support vector machine (SVM) and rules based methods like random forest (RF) and gradient boosted tree (GBT).
Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, we uniquely perform joint feature and label embedding by deriving a deep latent space, followed by the introduction of label-correlation sensitive loss function for recovering the predicted label outputs. Our C2AE is achieved by integrating the DNN architectures of canonical correlation analysis and autoencoder, which allows end-to-end learning and prediction with the ability to exploit label dependency. Moreover, our C2AE can be easily extended to address the learning problem with missing labels. Our experiments on multiple datasets with different scales confirm the effectiveness and robustness of our proposed method, which is shown to perform favorably against state-of-the-art methods for multi-label classification.
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic. It is therefore applicable without any modifications to a wide range of computer vision problems such as image classification, object detection and image segmentation. We present experimental results showing that this model improves the computational efficiency of Residual Networks on the challenging ImageNet classification and COCO object detection datasets. Additionally, we evaluate the computation time maps on the visual saliency dataset cat2000 and find that they correlate surprisingly well with human eye fixation positions.
The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very high-dimensional inputs due to the large input-to-hidden weight matrix. This may have prevented RNNs' large-scale application in tasks that involve very high input dimensions such as video modeling; current approaches reduce the input dimensions using various feature extractors. To address this challenge, we propose a new, more general and efficient approach by factorizing the input-to-hidden weight matrix using Tensor-Train decomposition which is trained simultaneously with the weights themselves. We test our model on classification tasks using multiple real-world video datasets and achieve competitive performances with state-of-the-art models, even though our model architecture is orders of magnitude less complex. We believe that the proposed approach provides a novel and fundamental building block for modeling high-dimensional sequential data with RNN architectures and opens up many possibilities to transfer the expressive and advanced architectures from other domains such as NLP to modeling high-dimensional sequential data.
This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems. We study the impact of different pretrained CNN feature extractors on the problem of image set clustering for object classification as well as fine-grained classification. We propose a rather straightforward pipeline combining deep-feature extraction using a CNN pretrained on ImageNet and a classic clustering algorithm to classify sets of images. This approach is compared to state-of-the-art algorithms in image-clustering and provides better results. These results strengthen the belief that supervised training of deep CNN on large datasets, with a large variability of classes, extracts better features than most carefully designed engineering approaches, even for unsupervised tasks. We also validate our approach on a robotic application, consisting in sorting and storing objects smartly based on clustering.
High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing classification problem. In this letter, crowdsourcing systems are exploited in order to enable the automatic acquisition and annotation of a large-scale satellite imagery database for crosswalks related tasks. Then, this dataset is used to train deep-learning-based models in order to accurately classify satellite images that contains or not zebra crossings. A novel dataset with more than 240,000 images from 3 continents, 9 countries and more than 20 cities was used in the experiments. Experimental results showed that freely available crowdsourcing data can be used to accurately (97.11%) train robust models to perform crosswalk classification on a global scale.
The enormous amount of texts published daily by Internet users has fostered the development of methods to analyze this content in several natural language processing areas, such as sentiment analysis. The main goal of this task is to classify the polarity of a message. Even though many approaches have been proposed for sentiment analysis, some of the most successful ones rely on the availability of large annotated corpus, which is an expensive and time-consuming process. In recent years, distant supervision has been used to obtain larger datasets. So, inspired by these techniques, in this paper we extend such approaches to incorporate popular graphic symbols used in electronic messages, the emojis, in order to create a large sentiment corpus for Portuguese. Trained on almost one million tweets, several models were tested in both same domain and cross-domain corpora. Our methods obtained very competitive results in five annotated corpora from mixed domains (Twitter and product reviews), which proves the domain-independent property of such approach. In addition, our results suggest that the combination of emoticons and emojis is able to properly capture the sentiment of a message.
Hashing methods have been widely used for applications of large-scale image retrieval and classification. Non-deep hashing methods using handcrafted features have been significantly outperformed by deep hashing methods due to their better feature representation and end-to-end learning framework. However, the most striking successes in deep hashing have mostly involved discriminative models, which require labels. In this paper, we propose a novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), for large-scale image retrieval and classification. In the proposed framework, we address two main problems: 1) how to directly learn discrete binary codes? 2) how to equip the binary representation with the ability of accurate image retrieval and classification in an unsupervised way? We resolve these problems by introducing an intermediate variable and a loss function steering the learning process, which is based on the neighborhood structure in the original space. Experimental results on standard datasets (CIFAR-10, NUS-WIDE, and Oxford-17) demonstrate that our DDH significantly outperforms existing hashing methods by large margin in terms of~mAP for image retrieval and object recognition. Code is available at \url{https://github.com/htconquer/ddh}.
The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one or more of 4,716 classes. In this Kaggle competition, we placed in the top 3% out of 650 participants using released video and audio features. Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text. The newly introduced text data is termed as YouTube-8M-Text. We present a classification framework for the joint use of text, visual and audio features, and conduct an extensive set of experiments to quantify the benefit that this additional mode brings. The inclusion of text yields state-of-the-art results, e.g. 86.7% GAP on the YouTube-8M-Text validation dataset.
Traditional sentiment analysis approaches tackle problems like ternary (3-category) and fine-grained (5-category) classification by learning the tasks separately. We argue that such classification tasks are correlated and we propose a multitask approach based on a recurrent neural network that benefits by jointly learning them. Our study demonstrates the potential of multitask models on this type of problems and improves the state-of-the-art results in the fine-grained sentiment classification problem.
This paper introduces the system we developed for the Youtube-8M Video Understanding Challenge, in which a large-scale benchmark dataset was used for multi-label video classification. The proposed framework contains hierarchical deep architecture, including the frame-level sequence modeling part and the video-level classification part. In the frame-level sequence modelling part, we explore a set of methods including Pooling-LSTM (PLSTM), Hierarchical-LSTM (HLSTM), Random-LSTM (RLSTM) in order to address the problem of large amount of frames in a video. We also introduce two attention pooling methods, single attention pooling (ATT) and multiply attention pooling (Multi-ATT) so that we can pay more attention to the informative frames in a video and ignore the useless frames. In the video-level classification part, two methods are proposed to increase the classification performance, i.e. Hierarchical-Mixture-of-Experts (HMoE) and Classifier Chains (CC). Our final submission is an ensemble consisting of 18 sub-models. In terms of the official evaluation metric Global Average Precision (GAP) at 20, our best submission achieves 0.84346 on the public 50% of test dataset and 0.84333 on the private 50% of test data.
In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates fixed-length raw representations by means of simple aggregation functions, which are then refined using an attention mechanism. Finally it combines the refined representations of both sentences into a single vector to be used for classification. With this model we obtained test accuracies of 72.057% and 72.055% in the matched and mismatched evaluation tracks respectively, outperforming the LSTM baseline, and obtaining performances similar to a model that relies on shared information between sentences (ESIM). When using an ensemble both accuracies increased to 72.247% and 72.827% respectively.
YouTube-8M is the largest video dataset for multi-label video classification. In order to tackle the multi-label classification on this challenging dataset, it is necessary to solve several issues such as temporal modeling of videos, label imbalances, and correlations between labels. We develop a deep neural network model, which consists of four components: the frame encoder, the classification layer, the label processing layer, and the loss function. We introduce our newly proposed methods and discusses how existing models operate in the YouTube-8M Classification Task, what insights they have, and why they succeed (or fail) to achieve good performance. Most of the models we proposed are very high compared to the baseline models, and the ensemble of the models we used is 8th in the Kaggle Competition.
We propose a novel method for automatic program synthesis. P-Tree Programming represents the program search space through a single probabilistic prototype tree. From this prototype tree we form program instances which we evaluate on a given problem. The error values from the evaluations are propagated through the prototype tree. We use them to update the probability distributions that determine the symbol choices of further instances. The iterative method is applied to several symbolic regression benchmarks from the literature. It outperforms standard Genetic Programming to a large extend. Furthermore, it relies on a concise set of parameters which are held constant for all problems. The algorithm can be employed for most of the typical computational intelligence tasks such as classification, automatic program induction, and symbolic regression.