Tiny object classification problem exists in many machine learning applications like medical imaging or remote sensing, where the object of interest usually occupies a small region of the whole image. It is challenging to design an efficient machine learning model with respect to tiny object of interest. Current neural network structures are unable to deal with tiny object efficiently because they are mainly developed for images featured by large scale objects. However, in quantum physics, there is a great theoretical foundation guiding us to analyze the target function for image classification regarding to specific objects size ratio. In our work, we apply Tensor Networks to solve this arising tough machine learning problem. First, we summarize the previous work that connects quantum spin model to image classification and bring the theory into the scenario of tiny object classification. Second, we propose using 2D multi-scale entanglement renormalization ansatz (MERA) to classify tiny objects in image. In the end, our experimental results indicate that tensor network models are effective for tiny object classification problem and potentially will beat state-of-the-art. Our codes will be available online https://github.com/timqqt/MERA_Image_Classification.
Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross-entropy loss). This setup dismisses all kinds of supporting signals that can be used to reinforce the existence or absence of a particular pattern. The increasing need for models that are interpretable by design makes the inclusion of said contextual signals a crucial necessity. To this end, we introduce the notion of Self-Supervised Autogenous Learning (SSAL) models. A SSAL objective is realized through one or more additional targets that are derived from the original supervised classification task, following architectural principles found in multi-task learning. SSAL branches impose low-level priors into the optimization process (e.g., grouping). The ability of using SSAL branches during inference, allow models to converge faster, focusing on a richer set of class-relevant features. We show that SSAL models consistently outperform the state-of-the-art while also providing structured predictions that are more interpretable.
A scalable semi-supervised node classification method on graph-structured data, called GraphHop, is proposed in this work. The graph contains attributes of all nodes but labels of a few nodes. The classical label propagation (LP) method and the emerging graph convolutional network (GCN) are two popular semi-supervised solutions to this problem. The LP method is not effective in modeling node attributes and labels jointly or facing a slow convergence rate on large-scale graphs. GraphHop is proposed to its shortcoming. With proper initial label vector embeddings, each iteration of GraphHop contains two steps: 1) label aggregation and 2) label update. In Step 1, each node aggregates its neighbors' label vectors obtained in the previous iteration. In Step 2, a new label vector is predicted for each node based on the label of the node itself and the aggregated label information obtained in Step 1. This iterative procedure exploits the neighborhood information and enables GraphHop to perform well in an extremely small label rate setting and scale well for very large graphs. Experimental results show that GraphHop outperforms state-of-the-art graph learning methods on a wide range of tasks (e.g., multi-label and multi-class classification on citation networks, social graphs, and commodity consumption graphs) in graphs of various sizes. Our codes are publicly available on GitHub (https://github.com/TianXieUSC/GraphHop).
While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making. Deploying learning systems in consequential settings also requires calibrating and communicating the uncertainty of predictions. To convey instance-wise uncertainty for prediction tasks, we show how to generate set-valued predictions from a black-box predictor that control the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any dataset by using a holdout set to calibrate the size of the prediction sets. This framework enables simple, distribution-free, rigorous error control for many tasks, and we demonstrate it in five large-scale machine learning problems: (1) classification problems where some mistakes are more costly than others; (2) multi-label classification, where each observation has multiple associated labels; (3) classification problems where the labels have a hierarchical structure; (4) image segmentation, where we wish to predict a set of pixels containing an object of interest; and (5) protein structure prediction. Lastly, we discuss extensions to uncertainty quantification for ranking, metric learning and distributionally robust learning.
Deep Neural Networks (DNNs) have become the de-facto standard in computer vision, as well as in many other pattern recognition tasks. A key drawback of DNNs is that the training phase can be very computationally expensive. Organizations or individuals that cannot afford purchasing state-of-the-art hardware or tapping into cloud-hosted infrastructures may face a long waiting time before the training completes or might not be able to train a model at all. Investigating novel ways to reduce the training time could be a potential solution to alleviate this drawback, and thus enabling more rapid development of new algorithms and models. In this paper, we propose LightLayers, a method for reducing the number of trainable parameters in deep neural networks (DNN). The proposed LightLayers consists of LightDense andLightConv2D layer that are as efficient as regular Conv2D and Dense layers, but uses less parameters. We resort to Matrix Factorization to reduce the complexity of the DNN models resulting into lightweight DNNmodels that require less computational power, without much loss in the accuracy. We have tested LightLayers on MNIST, Fashion MNIST, CI-FAR 10, and CIFAR 100 datasets. Promising results are obtained for MNIST, Fashion MNIST, CIFAR-10 datasets whereas CIFAR 100 shows acceptable performance by using fewer parameters.
In this paper, we analyze the feasibility of applying few-shot learning to speech emotion recognition task (SER). The current speech emotion recognition models work exceptionally well but fail when then input is multilingual. Moreover, when training such models, the models' performance is suitable only when the training corpus is vast. This availability of a big training corpus is a significant problem when choosing a language that is not much popular or obscure. We attempt to solve this challenge of multilingualism and lack of available data by turning this problem into a few-shot learning problem. We suggest relaxing the assumption that all N classes in an N-way K-shot problem be new and define an N+F way problem where N and F are the number of emotion classes and predefined fixed classes, respectively. We propose this modification to the Model-Agnostic MetaLearning (MAML) algorithm to solve the problem and call this new model F-MAML. This modification performs better than the original MAML and outperforms on EmoFilm dataset.
As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation method for the point cloud data, named PointCutMix, to alleviate those problems. It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs. Two replacement strategies are proposed to adapt to the accuracy or robustness requirement for different tasks, one of which is to randomly select all replacing points while the other one is to select k nearest neighbors of a single random point. Both strategies consistently and significantly improve the performance of various models on point cloud classification problems. By introducing the saliency maps to guide the selection of replacing points, the performance further improves. Moreover, PointCutMix is validated to enhance the model robustness against the point attack. It is worth noting that when using as a defense method, our method outperforms the state-of-the-art defense algorithms. The code is available at:https://github.com/cuge1995/PointCutMix
Understanding privacy policies is crucial for users as it empowers them to learn about the information that matters to them. Sentences written in a privacy policy document explain privacy practices, and the constituent text spans convey further specific information about that practice. We refer to predicting the privacy practice explained in a sentence as intent classification and identifying the text spans sharing specific information as slot filling. In this work, we propose PolicyIE, an English corpus consisting of 5,250 intent and 11,788 slot annotations spanning 31 privacy policies of websites and mobile applications. PolicyIE corpus is a challenging real-world benchmark with limited labeled examples reflecting the cost of collecting large-scale annotations from domain experts. We present two alternative neural approaches as baselines, (1) intent classification and slot filling as a joint sequence tagging and (2) modeling them as a sequence-to-sequence (Seq2Seq) learning task. The experiment results show that both approaches perform comparably in intent classification, while the Seq2Seq method outperforms the sequence tagging approach in slot filling by a large margin. We perform a detailed error analysis to reveal the challenges of the proposed corpus.
Joint Energy-based Model (JEM) of Grathwohl et al. shows that a standard softmax classifier can be reinterpreted as an energy-based model (EBM) for the joint distribution p(x,y); the resulting model can be optimized to improve calibration, robustness, and out-of-distribution detection, while generating samples rivaling the quality of recent GAN-based approaches. However, the softmax classifier that JEM exploits is inherently discriminative and its latent feature space is not well formulated as probabilistic distributions, which may hinder its potential for image generation and incur training instability. We hypothesize that generative classifiers, such as Linear Discriminant Analysis (LDA), might be more suitable for image generation since generative classifiers model the data generation process explicitly. This paper therefore investigates an LDA classifier for image classification and generation. In particular, the Max-Mahalanobis Classifier (MMC), a special case of LDA, fits our goal very well. We show that our Generative MMC (GMMC) can be trained discriminatively, generatively, or jointly for image classification and generation. Extensive experiments on multiple datasets show that GMMC achieves state-of-the-art discriminative and generative performances, while outperforming JEM in calibration, adversarial robustness, and out-of-distribution detection by a significant margin. Our source code is available at https://github.com/sndnyang/GMMC.
Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms on a variety of few-shot tasks.
BERT, as one of the pretrianed language models, attracts the most attention in recent years for creating new benchmarks across GLUE tasks via fine-tuning. One pressing issue is to open up the blackbox and explain the decision makings of BERT. A number of attribution techniques have been proposed to explain BERT models, but are often limited to sequence to sequence tasks. In this paper, we adapt existing attribution methods on explaining decision makings of BERT in sequence classification tasks. We conduct extensive analyses of four existing attribution methods by applying them to four different datasets in sentiment analysis. We compare the reliability and robustness of each method via various ablation studies. Furthermore, we test whether attribution methods explain generalized semantics across semantically similar tasks. Our work provides solid guidance for using attribution methods to explain decision makings of BERT for downstream classification tasks.
Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention and relies on an energy-based structure to model data probability distributions. Notwithstanding, such a technique is susceptible to adversarial manipulation, i.e., slightly or profoundly modified data. An alternative to overcome the adversarial problem lies in the Generative Adversarial Networks (GAN), capable of modeling data distributions and generating adversarial data that resemble the original ones. Therefore, this work proposes to artificially generate RBMs using Adversarial Learning, where pre-trained weight matrices serve as the GAN inputs. Furthermore, it proposes to sample copious amounts of matrices and combine them into ensembles, alleviating the burden of training new models'. Experimental results demonstrate the suitability of the proposed approach under image reconstruction and image classification tasks, and describe how artificial-based ensembles are alternatives to pre-training vast amounts of RBMs.
The availability of large amounts of data and compelling computation power have made deep learning models much popular for text classification and sentiment analysis. Deep neural networks have achieved competitive performance on the above tasks when trained on naive text representations such as word count, term frequency, and binary matrix embeddings. However, many of the above representations result in the input space having a dimension of the order of the vocabulary size, which is enormous. This leads to a blow-up in the number of parameters to be learned, and the computational cost becomes infeasible when scaling to domains that require retaining a colossal vocabulary. This work proposes using singular value decomposition to transform the high dimensional input space to a lower-dimensional latent space. We show that neural networks trained on this lower-dimensional space are not only able to retain performance while savoring significant reduction in the computational complexity but, in many situations, also outperforms the classical neural networks trained on the native input space.
We study the following problem: given two public transit station identifiers A and B, each with a label and a geographic coordinate, decide whether A and B describe the same station. For example, for "St Pancras International" at (51.5306, -0.1253) and "London St Pancras" at (51.5319, -0.1269), the answer would be "Yes". This problem frequently arises in areas where public transit data is used, for example in geographic information systems, schedule merging, route planning, or map matching. We consider several baseline methods based on geographic distance and simple string similarity measures. We also experiment with more elaborate string similarity measures and manually created normalization rules. Our experiments show that these baseline methods produce good, but not fully satisfactory results. We therefore develop an approach based on a random forest classifier which is trained on matching trigrams between two stations, their distance, and their position on an interwoven grid. All approaches are evaluated on extensive ground truth datasets we generated from OpenStreetMap (OSM) data: (1) The union of Great Britain and Ireland and (2) the union of Germany, Switzerland, and Austria. On all datasets, our learning-based approach achieves an F1 score of over 99%, while even the most elaborate baseline approach (based on TFIDF scores and the geographic distance) achieves an F1 score of at most 94%, and a naive approach of using a geographical distance threshold achieves an F1 score of only 75%. Both our training and testing datasets are publicly available.
Feature representation is an important aspect of remote-sensing based image classification. While deep convolutional neural networks are able to effectively amalgamate information, large numbers of parameters often make learned features inscrutable and difficult to transfer to alternative models. In order to better represent statistical texture information for remote-sensing image classification, in this paper, we investigate performing joint dimensionality reduction and classification using a novel histogram neural network. Motivated by a popular dimensionality reduction approach, t-Distributed Stochastic Neighbor Embedding (t-SNE), our proposed method incorporates a classification loss computed on samples in a low-dimensional embedding space. We compare the learned sample embeddings against coordinates found by t-SNE in terms of classification accuracy and qualitative assessment. We also explore use of various divergence measures in the t-SNE objective. The proposed method has several advantages such as readily embedding out-of-sample points and reducing feature dimensionality while retaining class discriminability. Our results show that the proposed approach maintains and/or improves classification performance and reveals characteristics of features produced by neural networks that may be helpful for other applications.
Asymmetric binary classification problems, in which the type I and II errors have unequal severity, are ubiquitous in real-world applications. To handle such asymmetry, researchers have developed the cost-sensitive and Neyman-Pearson paradigms for training classifiers to control the more severe type of classification error, say the type I error. The cost-sensitive paradigm is widely used and has straightforward implementations that do not require sample splitting; however, it demands an explicit specification of the costs of the type I and II errors, and an open question is what specification can guarantee a high-probability control on the population type I error. In contrast, the Neyman-Pearson paradigm can train classifiers to achieve a high-probability control of the population type I error, but it relies on sample splitting that reduces the effective training sample size. Since the two paradigms have complementary strengths, it is reasonable to combine their strengths for classifier construction. In this work, we for the first time study the methodological connections between the two paradigms, and we develop the TUBE-CS algorithm to bridge the two paradigms from the perspective of controlling the population type I error.
Semi-supervised learning has been gaining attention as it allows for performing image analysis tasks such as classification with limited labeled data. Some popular algorithms using Generative Adversarial Networks (GANs) for semi-supervised classification share a single architecture for classification and discrimination. However, this may require a model to converge to a separate data distribution for each task, which may reduce overall performance. While progress in semi-supervised learning has been made, less addressed are small-scale, fully-supervised tasks where even unlabeled data is unavailable and unattainable. We therefore, propose a novel GAN model namely External Classifier GAN (EC-GAN), that utilizes GANs and semi-supervised algorithms to improve classification in fully-supervised regimes. Our method leverages a GAN to generate artificial data used to supplement supervised classification. More specifically, we attach an external classifier, hence the name EC-GAN, to the GAN's generator, as opposed to sharing an architecture with the discriminator. Our experiments demonstrate that EC-GAN's performance is comparable to the shared architecture method, far superior to the standard data augmentation and regularization-based approach, and effective on a small, realistic dataset.
In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning.
Choosing a decision threshold is one of the challenging job in any classification tasks. How much the model is accurate, if the deciding boundary is not picked up carefully, its entire performance would go in vain. On the other hand, for imbalance classification where one of the classes is dominant over another, relying on the conventional method of choosing threshold would result in poor performance. Even if the threshold or decision boundary is properly chosen based on machine learning strategies like SVM and decision tree, it will fail at some point for dynamically varying databases and in case of identity-features that are more or less similar, like in face recognition and person re-identification models. Hence, with the need for adaptability of the decision threshold selection for imbalanced classification and incremental database size, an online optimization-based statistical feature learning adaptive technique is developed and tested on the LFW datasets and self-prepared athletes datasets. This method of adopting adaptive threshold resulted in 12-45% improvement in the model accuracy compared to the fixed threshold {0.3,0.5,0.7} that are usually taken via the hit-and-trial method in any classification and identification tasks. Source code for the complete algorithm is available at: https://github.com/Varat7v2/adaptive-threshold
The field of deep learning is evolving in different directions, with still the need for more efficient training strategies. In this work, we present a novel and robust training scheme that integrates visual explanation techniques in the learning process. Unlike the attention mechanisms that focus on the relevant parts of images, we aim to improve the robustness of the model by making it pay attention to other regions as well. Broadly speaking, the idea is to distract the classifier in the learning process to force it to focus not only on relevant regions but also on those that, a priori, are not so informative for the discrimination of the class. We tested the proposed approach by embedding it into the learning process of a convolutional neural network for the analysis and classification of two well-known datasets, namely Stanford cars and FGVC-Aircraft. Furthermore, we evaluated our model on a real-case scenario for the classification of egocentric images, allowing us to obtain relevant information about peoples' lifestyles. In particular, we work on the challenging EgoFoodPlaces dataset, achieving state-of-the-art results with a lower level of complexity. The obtained results indicate the suitability of our proposed training scheme for image classification, improving the robustness of the final model.