Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music and related styles. This leads to research questions on whether these models can be used to learn representations for different music cultures and styles, or whether we can build similar music audio embedding models trained on data from different cultures or styles. To that end, we leverage transfer learning methods to derive insights about the similarities between the different music cultures to which the data belongs to. We use two Western music datasets, two traditional/folk datasets coming from eastern Mediterranean cultures, and two datasets belonging to Indian art music. Three deep audio embedding models are trained and transferred across domains, including two CNN-based and a Transformer-based architecture, to perform auto-tagging for each target domain dataset. Experimental results show that competitive performance is achieved in all domains via transfer learning, while the best source dataset varies for each music culture. The implementation and the trained models are both provided in a public repository.
The COVID-19 pandemic has led to a global health crisis, highlighting the need for rapid and accurate virus detection. This research paper examines transfer learning with vision transformers for COVID-19 detection, known for its excellent performance in image recognition tasks. We leverage the capability of Vision Transformers to capture global context and learn complex patterns from chest X-ray images. In this work, we explored the recent state-of-art transformer models to detect Covid-19 using CXR images such as vision transformer (ViT), Swin-transformer, Max vision transformer (MViT), and Pyramid Vision transformer (PVT). Through the utilization of transfer learning with IMAGENET weights, the models achieved an impressive accuracy range of 98.75% to 99.5%. Our experiments demonstrate that Vision Transformers achieve state-of-the-art performance in COVID-19 detection, outperforming traditional methods and even Convolutional Neural Networks (CNNs). The results highlight the potential of Vision Transformers as a powerful tool for COVID-19 detection, with implications for improving the efficiency and accuracy of screening and diagnosis in clinical settings.
Introduction: Cases of throat cancer are rising worldwide. With survival decreasing significantly at later stages, early detection is vital. Artificial intelligence (AI) and machine learning (ML) have the potential to detect throat cancer from patient speech, facilitating earlier diagnosis and reducing the burden on overstretched healthcare systems. However, no comprehensive review has explored the use of AI and ML for detecting throat cancer from speech. This review aims to fill this gap by evaluating how these technologies perform and identifying issues that need to be addressed in future research. Materials and Methods: We conducted a scoping literature review across three databases: Scopus, Web of Science, and PubMed. We included articles that classified speech using machine learning and specified the inclusion of throat cancer patients in their data. Articles were categorized based on whether they performed binary or multi-class classification. Results: We found 27 articles fitting our inclusion criteria, 12 performing binary classification, 13 performing multi-class classification, and two that do both binary and multiclass classification. The most common classification method used was neural networks, and the most frequently extracted feature was mel-spectrograms. We also documented pre-processing methods and classifier performance. We compared each article against the TRIPOD-AI checklist, which showed a significant lack of open science, with only one article sharing code and only three using open-access data. Conclusion: Open-source code is essential for external validation and further development in this field. Our review indicates that no single method or specific feature consistently outperforms others in detecting throat cancer from speech. Future research should focus on standardizing methodologies and improving the reproducibility of results.
Multi-tenancy in public clouds may lead to co-location interference on shared resources, which possibly results in performance degradation of cloud applications. Cloud providers want to know when such events happen and how serious the degradation is, to perform interference-aware migrations and alleviate the problem. However, virtual machines (VM) in Infrastructure-as-a-Service public clouds are black-boxes to providers, where application-level performance information cannot be acquired. This makes performance monitoring intensely challenging as cloud providers can only rely on low-level metrics such as CPU usage and hardware counters. We propose a novel machine learning framework, Alioth, to monitor the performance degradation of cloud applications. To feed the data-hungry models, we first elaborate interference generators and conduct comprehensive co-location experiments on a testbed to build Alioth-dataset which reflects the complexity and dynamicity in real-world scenarios. Then we construct Alioth by (1) augmenting features via recovering low-level metrics under no interference using denoising auto-encoders, (2) devising a transfer learning model based on domain adaptation neural network to make models generalize on test cases unseen in offline training, and (3) developing a SHAP explainer to automate feature selection and enhance model interpretability. Experiments show that Alioth achieves an average mean absolute error of 5.29% offline and 10.8% when testing on applications unseen in the training stage, outperforming the baseline methods. Alioth is also robust in signaling quality-of-service violation under dynamicity. Finally, we demonstrate a possible application of Alioth's interpretability, providing insights to benefit the decision-making of cloud operators. The dataset and code of Alioth have been released on GitHub.
Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or object-relationships) where their performance is no better than random chance. To address this, we introduce SDS-CLIP, a lightweight and sample-efficient distillation method to enhance CLIP's compositional visio-linguistic reasoning. Our approach fine-tunes CLIP using a distillation objective borrowed from large text-to-image generative models like Stable-Diffusion, which are known for their strong visio-linguistic reasoning abilities. On the challenging Winoground benchmark, SDS-CLIP improves the visio-linguistic performance of various CLIP models by up to 7%, while on the ARO dataset, it boosts performance by up to 3%. This work underscores the potential of well-designed distillation objectives from generative models to enhance contrastive image-text models with improved visio-linguistic reasoning capabilities.
As the most fundamental scene understanding tasks, object detection and segmentation have made tremendous progress in deep learning era. Due to the expensive manual labeling cost, the annotated categories in existing datasets are often small-scale and pre-defined, i.e., state-of-the-art fully-supervised detectors and segmentors fail to generalize beyond the closed vocabulary. To resolve this limitation, in the last few years, the community has witnessed an increasing attention toward Open-Vocabulary Detection (OVD) and Segmentation (OVS). By ``open-vocabulary'', we mean that the models can classify objects beyond pre-defined categories. In this survey, we provide a comprehensive review on recent developments of OVD and OVS. A taxonomy is first developed to organize different tasks and methodologies. We find that the permission and usage of weak supervision signals can well discriminate different methodologies, including: visual-semantic space mapping, novel visual feature synthesis, region-aware training, pseudo-labeling, knowledge distillation, and transfer learning. The proposed taxonomy is universal across different tasks, covering object detection, semantic/instance/panoptic segmentation, 3D and video understanding. The main design principles, key challenges, development routes, methodology strengths, and weaknesses are thoroughly analyzed. In addition, we benchmark each task along with the vital components of each method in appendix and updated online at https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation. Finally, several promising directions are provided and discussed to stimulate future research.
We tackle the problem of novel class discovery, which aims to learn novel classes without supervision based on labeled data from known classes. A key challenge lies in transferring the knowledge in the known-class data to the learning of novel classes. Previous methods mainly focus on building a shared representation space for knowledge transfer and often ignore modeling class relations. To address this, we introduce a class relation representation for the novel classes based on the predicted class distribution of a model trained on known classes. Empirically, we find that such class relation becomes less informative during typical discovery training. To prevent such information loss, we propose a novel knowledge distillation framework, which utilizes our class-relation representation to regularize the learning of novel classes. In addition, to enable a flexible knowledge distillation scheme for each data point in novel classes, we develop a learnable weighting function for the regularization, which adaptively promotes knowledge transfer based on the semantic similarity between the novel and known classes. To validate the effectiveness and generalization of our method, we conduct extensive experiments on multiple benchmarks, including CIFAR100, Stanford Cars, CUB, and FGVC-Aircraft datasets. Our results demonstrate that the proposed method outperforms the previous state-of-the-art methods by a significant margin on almost all benchmarks. Code is available at \href{https://github.com/kleinzcy/Cr-KD-NCD}{here}.
Fetal head segmentation is a crucial step in measuring the fetal head circumference (HC) during gestation, an important biometric in obstetrics for monitoring fetal growth. However, manual biometry generation is time-consuming and results in inconsistent accuracy. To address this issue, convolutional neural network (CNN) models have been utilized to improve the efficiency of medical biometry. But training a CNN network from scratch is a challenging task, we proposed a Transfer Learning (TL) method. Our approach involves fine-tuning (FT) a U-Net network with a lightweight MobileNet as the encoder to perform segmentation on a set of fetal head ultrasound (US) images with limited effort. This method addresses the challenges associated with training a CNN network from scratch. It suggests that our proposed FT strategy yields segmentation performance that is comparable when trained with a reduced number of parameters by 85.8%. And our proposed FT strategy outperforms other strategies with smaller trainable parameter sizes below 4.4 million. Thus, we contend that it can serve as a dependable FT approach for reducing the size of models in medical image analysis. Our key findings highlight the importance of the balance between model performance and size in developing Artificial Intelligence (AI) applications by TL methods. Code is available at https://github.com/13204942/FT_Methods_for_Fetal_Head_Segmentation.
With the surge in emerging technologies such as Metaverse, spatial computing, and generative AI, the application of facial style transfer has gained a lot of interest from researchers as well as startups enthusiasts alike. StyleGAN methods have paved the way for transfer-learning strategies that could reduce the dependency on the huge volume of data that is available for the training process. However, StyleGAN methods have the tendency of overfitting that results in the introduction of artifacts in the facial images. Studies, such as DualStyleGAN, proposed the use of multipath networks but they require the networks to be trained for a specific style rather than generating a fusion of facial styles at once. In this paper, we propose a FusIon of STyles (FIST) network for facial images that leverages pre-trained multipath style transfer networks to eliminate the problem associated with lack of huge data volume in the training phase along with the fusion of multiple styles at the output. We leverage pre-trained styleGAN networks with an external style pass that use residual modulation block instead of a transform coding block. The method also preserves facial structure, identity, and details via the gated mapping unit introduced in this study. The aforementioned components enable us to train the network with very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient, flexible style and model fusion in the generative space. We perform extensive experiments to show the superiority of FISTNet in comparison to existing state-of-the-art methods.
Coping with distributional shifts is an important part of transfer learning methods in order to perform well in real-life tasks. However, most of the existing approaches in this area either focus on an ideal scenario in which the data does not contain noises or employ a complicated training paradigm or model design to deal with distributional shifts. In this paper, we revisit the robustness of the minimum error entropy (MEE) criterion, a widely used objective in statistical signal processing to deal with non-Gaussian noises, and investigate its feasibility and usefulness in real-life transfer learning regression tasks, where distributional shifts are common. Specifically, we put forward a new theoretical result showing the robustness of MEE against covariate shift. We also show that by simply replacing the mean squared error (MSE) loss with the MEE on basic transfer learning algorithms such as fine-tuning and linear probing, we can achieve competitive performance with respect to state-of-the-art transfer learning algorithms. We justify our arguments on both synthetic data and 5 real-world time-series data.
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Classifying player actions from soccer videos is a challenging problem, which has become increasingly important in sports analytics over the years. Most state-of-the-art methods employ highly complex offline networks, which makes it difficult to deploy such models in resource constrained scenarios. Here, in this paper we propose a novel end-to-end knowledge distillation based transfer learning network pre-trained on the Kinetics400 dataset and then perform extensive analysis on the learned framework by introducing a unique loss parameterization. We also introduce a new dataset named SoccerDB1 containing 448 videos and consisting of 4 diverse classes each of players playing soccer. Furthermore, we introduce an unique loss parameter that help us linearly weigh the extent to which the predictions of each network are utilized. Finally, we also perform a thorough performance study using various changed hyperparameters. We also benchmark the first classification results on the new SoccerDB1 dataset obtaining 67.20% validation accuracy. Apart from outperforming prior arts significantly, our model also generalizes to new datasets easily. The dataset has been made publicly available at: https://bit.ly/soccerdb1
Distilling knowledge from convolutional neural networks (CNNs) is a double-edged sword for vision transformers (ViTs). It boosts the performance since the image-friendly local-inductive bias of CNN helps ViT learn faster and better, but leading to two problems: (1) Network designs of CNN and ViT are completely different, which leads to different semantic levels of intermediate features, making spatial-wise knowledge transfer methods (e.g., feature mimicking) inefficient. (2) Distilling knowledge from CNN limits the network convergence in the later training period since ViT's capability of integrating global information is suppressed by CNN's local-inductive-bias supervision. To this end, we present Cumulative Spatial Knowledge Distillation (CSKD). CSKD distills spatial-wise knowledge to all patch tokens of ViT from the corresponding spatial responses of CNN, without introducing intermediate features. Furthermore, CSKD exploits a Cumulative Knowledge Fusion (CKF) module, which introduces the global response of CNN and increasingly emphasizes its importance during the training. Applying CKF leverages CNN's local inductive bias in the early training period and gives full play to ViT's global capability in the later one. Extensive experiments and analysis on ImageNet-1k and downstream datasets demonstrate the superiority of our CSKD. Code will be publicly available.
Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks were generated from the target domain using a novel conventional image processing ventricular segmentation algorithm and used to supplement the gold standard (GS) data from the source domain, Canadian Atherosclerosis Imaging Network (CAIN). Four models were tested on held-out test sets from four datasets: 1) SS+GS: trained on target SS masks and fine-tuned on source GS masks, 2) GS+SS: trained on source GS masks and fine-tuned on target SS masks, 3) trained on source GS (GS CAIN Only) and 4) trained on target SS masks (SS Only). The SS+GS model had the best and most consistent performance (mean DSC = 0.89, CoV = 0.05) and showed significantly (p < 0.05) higher DSC compared to the GS-only model on three target domains. Results suggest pre-training with noisy labels from the target domain allows the model to adapt to the dataset-specific characteristics and provides robust parameter initialization while fine-tuning with GS masks allows the model to learn detailed features. This method has wide application to other medical imaging problems where labeled data is scarce, and can be used as a per-dataset calibration method to accelerate wide-scale adoption.
Due to the lack of enough real multi-agent data and time-consuming of labeling, existing multi-agent cooperative perception algorithms usually select the simulated sensor data for training and validating. However, the perception performance is degraded when these simulation-trained models are deployed to the real world, due to the significant domain gap between the simulated and real data. In this paper, we propose the first Simulation-to-Reality transfer learning framework for multi-agent cooperative perception using a novel Vision Transformer, named as S2R-ViT, which considers both the Deployment Gap and Feature Gap between simulated and real data. We investigate the effects of these two types of domain gaps and propose a novel uncertainty-aware vision transformer to effectively relief the Deployment Gap and an agent-based feature adaptation module with inter-agent and ego-agent discriminators to reduce the Feature Gap. Our intensive experiments on the public multi-agent cooperative perception datasets OPV2V and V2V4Real demonstrate that the proposed S2R-ViT can effectively bridge the gap from simulation to reality and outperform other methods significantly for point cloud-based 3D object detection.
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both families of tasks simultaneously. We identify diffusion models as a prime candidate. Diffusion models have risen to prominence as a state-of-the-art method for image generation, denoising, inpainting, super-resolution, manipulation, etc. Such models involve training a U-Net to iteratively predict and remove noise, and the resulting model can synthesize high fidelity, diverse, novel images. The U-Net architecture, as a convolution-based architecture, generates a diverse set of feature representations in the form of intermediate feature maps. We present our findings that these embeddings are useful beyond the noise prediction task, as they contain discriminative information and can also be leveraged for classification. We explore optimal methods for extracting and using these embeddings for classification tasks, demonstrating promising results on the ImageNet classification task. We find that with careful feature selection and pooling, diffusion models outperform comparable generative-discriminative methods such as BigBiGAN for classification tasks. We investigate diffusion models in the transfer learning regime, examining their performance on several fine-grained visual classification datasets. We compare these embeddings to those generated by competing architectures and pre-trainings for classification tasks.
Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models can learn from large-scale public datasets like MS MARCO through transfer learning, evidence shows that not all DR models and domains can benefit from transfer learning equally. Recently, some researchers have resorted to large language models (LLMs) to improve the zero-shot and few-shot DR models. However, the hard prompts or human-written prompts utilized in these works cannot guarantee the good quality of generated weak queries. To tackle this, we propose soft prompt tuning for augmenting DR (SPTAR): For each task, we leverage soft prompt-tuning to optimize a task-specific soft prompt on limited ground truth data and then prompt the LLMs to tag unlabeled documents with weak queries, yielding enough weak document-query pairs to train task-specific dense retrievers. We design a filter to select high-quality example document-query pairs in the prompt to further improve the quality of weak tagged queries. To the best of our knowledge, there is no prior work utilizing soft prompt tuning to augment DR models. The experiments demonstrate that SPTAR outperforms the unsupervised baselines BM25 and the recently proposed LLMs-based augmentation method for DR.
The interpretability of deep neural networks has become a subject of great interest within the medical and healthcare domain. This attention stems from concerns regarding transparency, legal and ethical considerations, and the medical significance of predictions generated by these deep neural networks in clinical decision support systems. To address this matter, our study delves into the application of four well-established interpretability methods: Local Interpretable Model-agnostic Explanations (LIME), Shapley Additive exPlanations (SHAP), Gradient-weighted Class Activation Mapping (Grad-CAM), and Layer-wise Relevance Propagation (LRP). Leveraging the approach of transfer learning with a multi-label-multi-class chest radiography dataset, we aim to interpret predictions pertaining to specific pathology classes. Our analysis encompasses both single-label and multi-label predictions, providing a comprehensive and unbiased assessment through quantitative and qualitative investigations, which are compared against human expert annotation. Notably, Grad-CAM demonstrates the most favorable performance in quantitative evaluation, while the LIME heatmap score segmentation visualization exhibits the highest level of medical significance. Our research underscores both the outcomes and the challenges faced in the holistic approach adopted for assessing these interpretability methods and suggests that a multimodal-based approach, incorporating diverse sources of information beyond chest radiography images, could offer additional insights for enhancing interpretability in the medical domain.
While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of languages and speakers. Transfer learning enables the adaptation of large-scale multilingual models to not only low-resource languages but also to more specific speaker groups. However, fine-tuning on data from new domains is usually accompanied by a decrease in performance on the original domain. Therefore, in our experiments, we examine how well the performance of large-scale ASR models can be approximated for smaller domains, with our own dataset of German Senior Voice Commands (SVC-de), and how much of the general speech recognition performance can be preserved by selectively freezing parts of the model during training. To further increase the robustness of the ASR model to vocabulary and speakers outside of the fine-tuned domain, we apply Experience Replay for continual learning. By adding only a fraction of data from the original domain, we are able to reach Word-Error-Rates (WERs) below 5\% on the new domain, while stabilizing performance for general speech recognition at acceptable WERs.
Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers. However, the vanilla BERT uses the same self-attention mechanism for each layer to model the different contextual features. In this paper, we propose a HybridBERT model which combines self-attention and pooling networks to encode different contextual features in each layer. Additionally, we propose a simple DropMask method to address the mismatch between pre-training and fine-tuning caused by excessive use of special mask tokens during Masked Language Modeling pre-training. Experiments show that HybridBERT outperforms BERT in pre-training with lower loss, faster training speed (8% relative), lower memory cost (13% relative), and also in transfer learning with 1.5% relative higher accuracies on downstream tasks. Additionally, DropMask improves accuracies of BERT on downstream tasks across various masking rates.