This article presents a benchmark study of symbolic piano music classification using the masked language modelling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, we consider two types of MIDI data: MIDI scores, which are musical scores rendered directly into MIDI with no dynamics and precisely aligned with the metrical grid notated by its composer and MIDI performances, which are MIDI encodings of human performances of musical scoresheets. With five public-domain datasets of single-track piano MIDI files, we pre-train two 12-layer Transformer models using the BERT approach, one for MIDI scores and the other for MIDI performances, and fine-tune them for four downstream classification tasks. These include two note-level classification tasks (melody extraction and velocity prediction) and two sequence-level classification tasks (style classification and emotion classification). Our evaluation shows that the BERT approach leads to higher classification accuracy than recurrent neural network (RNN)-based baselines.
Optical coherence tomography angiography (OCTA) is a novel non-invasive imaging technique that allows visualizations of vasculature and foveal avascular zone (FAZ) across retinal layers. Clinical researches suggest that the morphology and contour irregularity of FAZ are important biomarkers of various ocular pathologies. Therefore, precise segmentation of FAZ has great clinical interest. Also, there is no existing research reporting that FAZ features can improve the performance of deep diagnostic classification networks. In this paper, we propose a novel multi-level boundary shape and distance aware joint learning framework, named BSDA-Net, for FAZ segmentation and diagnostic classification from OCTA images. Two auxiliary branches, namely boundary heatmap regression and signed distance map reconstruction branches, are constructed in addition to the segmentation branch to improve the segmentation performance, resulting in more accurate FAZ contours and fewer outliers. Moreover, both low-level and high-level features from the aforementioned three branches, including shape, size, boundary, and signed directional distance map of FAZ, are fused hierarchically with features from the diagnostic classifier. Through extensive experiments, the proposed BSDA-Net is found to yield state-of-the-art segmentation and classification results on the OCTA-500, OCTAGON, and FAZID datasets.
Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a clear need for developing explainable artificial intelligence mechanisms. There exist model-agnostic methods that summarize feature contributions, but their interpretability is limited to predictions made by black-box models. An open challenge is to develop models that have intrinsic interpretability and produce their own explanations, even for classes of models that are traditionally considered black boxes like (recurrent) neural networks. In this paper, we propose a Long-Term Cognitive Network for interpretable pattern classification of structured data. Our method brings its own mechanism for providing explanations by quantifying the relevance of each feature in the decision process. For supporting the interpretability without affecting the performance, the model incorporates more flexibility through a quasi-nonlinear reasoning rule that allows controlling nonlinearity. Besides, we propose a recurrence-aware decision model that evades the issues posed by the unique fixed point while introducing a deterministic learning algorithm to compute the tunable parameters. The simulations show that our interpretable model obtains competitive results when compared to state-of-the-art white and black-box models.
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance. However, the long-standing quantization error problem in the 2D heatmap-based methods leads to several well-known drawbacks: 1) The performance for the low-resolution inputs is limited; 2) To improve the feature map resolution for higher localization precision, multiple costly upsampling layers are required; 3) Extra post-processing is adopted to reduce the quantization error. To address these issues, we aim to explore a brand new scheme, called \textit{SimCC}, which reformulates HPE as two classification tasks for horizontal and vertical coordinates. The proposed SimCC uniformly divides each pixel into several bins, thus achieving \emph{sub-pixel} localization precision and low quantization error. Benefiting from that, SimCC can omit additional refinement post-processing and exclude upsampling layers under certain settings, resulting in a more simple and effective pipeline for HPE. Extensive experiments conducted over COCO, CrowdPose, and MPII datasets show that SimCC outperforms heatmap-based counterparts, especially in low-resolution settings by a large margin.
A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard concentration fails to fully characterize the intrinsic robustness of a classification problem since it ignores data labels which are essential to any classification task. Building on a novel definition of label uncertainty, we empirically demonstrate that error regions induced by state-of-the-art models tend to have much higher label uncertainty than randomly-selected subsets. This observation motivates us to adapt a concentration estimation algorithm to account for label uncertainty, resulting in more accurate intrinsic robustness measures for benchmark image classification problems.
The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher framework which is more robust to perturbations, can help mitigate the over-fitting effect. However, directly transferring KD from computer vision to medical image classification yields inferior performance as medical images suffer from higher intra-class variance and class imbalance. To address these issues, we propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. Specifically, we propose a novel Class-guided Contrastive Distillation (CCD) module to pull closer positive image pairs from the same class in the teacher and student models, while pushing apart negative image pairs from different classes. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. Besides, we propose a Categorical Relation Preserving (CRP) loss to distill the teacher's relational knowledge in a robust and class-balanced manner. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively. Extensive experiments on the HAM10000 and APTOS datasets demonstrate the superiority of the proposed CRCKD method.
Hyperspectral (HS) images are characterized by approximately contiguous spectral information, enabling the fine identification of materials by capturing subtle spectral discrepancies. Owing to their excellent locally contextual modeling ability, convolutional neural networks (CNNs) have been proven to be a powerful feature extractor in HS image classification. However, CNNs fail to mine and represent the sequence attributes of spectral signatures well due to the limitations of their inherent network backbone. To solve this issue, we rethink HS image classification from a sequential perspective with transformers, and propose a novel backbone network called \ul{SpectralFormer}. Beyond band-wise representations in classic transformers, SpectralFormer is capable of learning spectrally local sequence information from neighboring bands of HS images, yielding group-wise spectral embeddings. More significantly, to reduce the possibility of losing valuable information in the layer-wise propagation process, we devise a cross-layer skip connection to convey memory-like components from shallow to deep layers by adaptively learning to fuse "soft" residuals across layers. It is worth noting that the proposed SpectralFormer is a highly flexible backbone network, which can be applicable to both pixel- and patch-wise inputs. We evaluate the classification performance of the proposed SpectralFormer on three HS datasets by conducting extensive experiments, showing the superiority over classic transformers and achieving a significant improvement in comparison with state-of-the-art backbone networks. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_SpectralFormer for the sake of reproducibility.
For early breast cancer detection, regular screening with mammography imaging is recommended. Routinary examinations result in datasets with a predominant amount of negative samples. A potential solution to such class-imbalance is joining forces across multiple institutions. Developing a collaborative computer-aided diagnosis system is challenging in different ways. Patient privacy and regulations need to be carefully respected. Data across institutions may be acquired from different devices or imaging protocols, leading to heterogeneous non-IID data. Also, for learning-based methods, new optimization strategies working on distributed data are required. Recently, federated learning has emerged as an effective tool for collaborative learning. In this setting, local models perform computation on their private data to update the global model. The order and the frequency of local updates influence the final global model. Hence, the order in which samples are locally presented to the optimizers plays an important role. In this work, we define a memory-aware curriculum learning method for the federated setting. Our curriculum controls the order of the training samples paying special attention to those that are forgotten after the deployment of the global model. Our approach is combined with unsupervised domain adaptation to deal with domain shift while preserving data privacy. We evaluate our method with three clinical datasets from different vendors. Our results verify the effectiveness of federated adversarial learning for the multi-site breast cancer classification. Moreover, we show that our proposed memory-aware curriculum method is beneficial to further improve classification performance. Our code is publicly available at: https://github.com/ameliajimenez/curriculum-federated-learning.
Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks for computer vision. The attention mechanism of transformers scales quadratically with the length of the input sequence, and unrolled images have long sequence lengths. Plus, transformers lack an inductive bias that is appropriate for images. We tested three modifications to vision transformer (ViT) architectures that address these shortcomings. Firstly, we alleviate the quadratic bottleneck by using linear attention mechanisms, called X-formers (such that, X in {Performer, Linformer, Nystr\"omformer}), thereby creating Vision X-formers (ViXs). This resulted in up to a seven times reduction in the GPU memory requirement. We also compared their performance with FNet and multi-layer perceptron mixers, which further reduced the GPU memory requirement. Secondly, we introduced an inductive bias for images by replacing the initial linear embedding layer by convolutional layers in ViX, which significantly increased classification accuracy without increasing the model size. Thirdly, we replaced the learnable 1D position embeddings in ViT with Rotary Position Embedding (RoPE), which increases the classification accuracy for the same model size. We believe that incorporating such changes can democratize transformers by making them accessible to those with limited data and computing resources.
Aggregating multiple sources of weak supervision (WS) can ease the data-labeling bottleneck prevalent in many machine learning applications, by replacing the tedious manual collection of ground truth labels. Current state of the art approaches that do not use any labeled training data, however, require two separate modeling steps: Learning a probabilistic latent variable model based on the WS sources -- making assumptions that rarely hold in practice -- followed by downstream model training. Importantly, the first step of modeling does not consider the performance of the downstream model. To address these caveats we propose an end-to-end approach for directly learning the downstream model by maximizing its agreement with probabilistic labels generated by reparameterizing previous probabilistic posteriors with a neural network. Our results show improved performance over prior work in terms of end model performance on downstream test sets, as well as in terms of improved robustness to dependencies among weak supervision sources.
The vast majority of statistical theory on binary classification characterizes performance in terms of accuracy. However, accuracy is known in many cases to poorly reflect the practical consequences of classification error, most famously in imbalanced binary classification, where data are dominated by samples from one of two classes. The first part of this paper derives a novel generalization of the Bayes-optimal classifier from accuracy to any performance metric computed from the confusion matrix. Specifically, this result (a) demonstrates that stochastic classifiers sometimes outperform the best possible deterministic classifier and (b) removes an empirically unverifiable absolute continuity assumption that is poorly understood but pervades existing results. We then demonstrate how to use this generalized Bayes classifier to obtain regret bounds in terms of the error of estimating regression functions under uniform loss. Finally, we use these results to develop some of the first finite-sample statistical guarantees specific to imbalanced binary classification. Specifically, we demonstrate that optimal classification performance depends on properties of class imbalance, such as a novel notion called Uniform Class Imbalance, that have not previously been formalized. We further illustrate these contributions numerically in the case of $k$-nearest neighbor classification
Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are suffering from a catastrophic forgetting problem, which is not studied extensively. In this paper, we make the first attempt to tackle the catastrophic forgetting problem in the mainstream self-supervised methods, i.e., contrastive learning methods. Specifically, we first develop a rehearsal-based framework combined with a novel sampling strategy and a self-supervised knowledge distillation to transfer information over time efficiently. Then, we propose an extra sample queue to help the network separate the feature representations of old and new data in the embedding space. Experimental results show that compared with the naive self-supervised baseline, which learns tasks one by one without taking any technique, we improve the image classification accuracy by 1.60% on CIFAR-100, 2.86% on ImageNet-Sub, and 1.29% on ImageNet-Full under 10 incremental steps setting. Our code will be available at https://github.com/VDIGPKU/ContinualContrastiveLearning.
Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones. In this paper, we point out the two types of artificial node features, i.e., positional and structural node features, and provide insights on why each of them is more appropriate for certain tasks, i.e., positional node classification, structural node classification, and graph classification. Extensive experimental results on 10 benchmark datasets validate our insights, thus leading to a practical guideline on the choices between different artificial node features for GNNs on non-attributed graphs. The code is available at https://github.com/zjzijielu/gnn-positional-structural-node-features.
In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine modern neural networks (normalizing flows) and traditional generative models (hidden Markov models - HMMs). Normalizing flow-based mixture models (NMMs) are used to model the conditional probability distribution given the hidden state in the HMMs. Model parameters are learned through judicious combinations of time-tested Bayesian learning methods and contemporary neural network learning methods. We mainly combine expectation-maximization (EM) and mini-batch gradient descent. The proposed generative models can compute likelihood of a data and hence directly suitable for maximum-likelihood (ML) classification approach. Due to structural flexibility of HMMs, we can use different normalizing flow models. This leads to different types of HMMs providing diversity in data modeling capacity. The diversity provides an opportunity for easy decision fusion from different models. For a standard speech phone classification setup involving 39 phones (classes) and the TIMIT dataset, we show that the use of standard features called mel-frequency-cepstral-coeffcients (MFCCs), the proposed generative models, and the decision fusion together can achieve $86.6\%$ accuracy by generative training only. This result is close to state-of-the-art results, for examples, $86.2\%$ accuracy of PyTorch-Kaldi toolkit [1], and $85.1\%$ accuracy using light gated recurrent units [2]. We do not use any discriminative learning approach and related sophisticated features in this article.
Federated learning is promising for its capability to collaboratively train models with multiple clients without accessing their data, but vulnerable when clients' data distributions diverge from each other. This divergence further leads to a dilemma: "Should we prioritize the learned model's generic performance (for future use at the server) or its personalized performance (for each client)?" These two, seemingly competing goals have divided the community to focus on one or the other, yet in this paper we show that it is possible to approach both at the same time. Concretely, we propose a novel federated learning framework that explicitly decouples a model's dual duties with two prediction tasks. On the one hand, we introduce a family of losses that are robust to non-identical class distributions, enabling clients to train a generic predictor with a consistent objective across them. On the other hand, we formulate the personalized predictor as a lightweight adaptive module that is learned to minimize each client's empirical risk on top of the generic predictor. With this two-loss, two-predictor framework which we name Federated Robust Decoupling (Fed-RoD), the learned model can simultaneously achieve state-of-the-art generic and personalized performance, essentially bridging the two tasks.
We provide a data-driven algorithm to classify market regimes for time series. We utilise the path signature, encoding time series into easy-to-describe objects, and provide a metric structure which establishes a connection between separation of regimes and clustering of points.
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction among spatial locations from raw data. The complexity of self-attention and MLP grows quadratically as the image size increases, which makes these models hard to scale up when high-resolution features are required. In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our architecture replaces the self-attention layer in vision transformers with three key operations: a 2D discrete Fourier transform, an element-wise multiplication between frequency-domain features and learnable global filters, and a 2D inverse Fourier transform. We exhibit favorable accuracy/complexity trade-offs of our models on both ImageNet and downstream tasks. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness. Code is available at https://github.com/raoyongming/GFNet
In this paper, a robust classification-autoencoder (CAE) is proposed, which has strong ability to recognize outliers and defend adversaries. The main idea is to change the autoencoder from an unsupervised learning model into a classifier, where the encoder is used to compress samples with different labels into disjoint compression spaces and the decoder is used to recover samples from their compression spaces. The encoder is used both as a compressed feature learner and as a classifier, and the decoder is used to decide whether the classification given by the encoder is correct by comparing the input sample with the output. Since adversary samples are seemingly inevitable for the current DNN framework, the list classifier to defend adversaries is introduced based on CAE, which outputs several labels and the corresponding samples recovered by the CAE. Extensive experimental results are used to show that the CAE achieves state of the art to recognize outliers by finding almost all outliers; the list classifier gives near lossless classification in the sense that the output list contains the correct label for almost all adversaries and the size of the output list is reasonably small.
Model-agnostic meta-learning (MAML) is arguably one of the most popular meta-learning algorithms nowadays. Nevertheless, its performance on few-shot classification is far behind many recent algorithms dedicated to the problem. In this paper, we point out several key facets of how to train MAML to excel in few-shot classification. First, we find that MAML needs a large number of gradient steps in its inner loop update, which contradicts its common usage in few-shot classification. Second, we find that MAML is sensitive to the class label assignments during meta-testing. Concretely, MAML meta-trains the initialization of an $N$-way classifier. These $N$ ways, during meta-testing, then have "$N!$" different permutations to be paired with a few-shot task of $N$ novel classes. We find that these permutations lead to a huge variance of accuracy, making MAML unstable in few-shot classification. Third, we investigate several approaches to make MAML permutation-invariant, among which meta-training a single vector to initialize all the $N$ weight vectors in the classification head performs the best. On benchmark datasets like MiniImageNet and TieredImageNet, our approach, which we name UNICORN-MAML, performs on a par with or even outperforms many recent few-shot classification algorithms, without sacrificing MAML's simplicity.
Consistently high data quality is essential for the development of novel loss functions and architectures in the field of deep learning. The existence of such data and labels is usually presumed, while acquiring high-quality datasets is still a major issue in many cases. In real-world datasets we often encounter ambiguous labels due to subjective annotations by annotators. In our data-centric approach, we propose a method to relabel such ambiguous labels instead of implementing the handling of this issue in a neural network. A hard classification is by definition not enough to capture the real-world ambiguity of the data. Therefore, we propose our method "Data-Centric Classification & Clustering (DC3)" which combines semi-supervised classification and clustering. It automatically estimates the ambiguity of an image and performs a classification or clustering depending on that ambiguity. DC3 is general in nature so that it can be used in addition to many Semi-Supervised Learning (SSL) algorithms. On average, this results in a 7.6% better F1-Score for classifications and 7.9% lower inner distance of clusters across multiple evaluated SSL algorithms and datasets. Most importantly, we give a proof-of-concept that the classifications and clusterings from DC3 are beneficial as proposals for the manual refinement of such ambiguous labels. Overall, a combination of SSL with our method DC3 can lead to better handling of ambiguous labels during the annotation process.