PyTorchKR Papers

최신 논문

총 10,241편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.02239

Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR

Transferring linguistic knowledge from a pretrained language model (PLM) to an acoustic model has been shown to greatly improve the performance of automatic speech recognition (ASR). However, due to the heterogeneous feature distributions in cross-modalities, designing an effective model for feature alignment and knowledge transfer between linguistic and acoustic sequences remains a challenging task. Optimal transport (OT), which efficiently measures probability distribution discrepancies, holds great potential for aligning and transferring knowledge between acoustic and linguistic modalities. Nonetheless, the original OT treats acoustic and linguistic feature sequences as two unordered sets in alignment and neglects temporal order information during OT coupling estimation. Consequently, a time-consuming pretraining stage is required to learn a good alignment between the acoustic and linguistic representations. In this paper, we propose a Temporal Order Preserved OT (TOT)-based Cross-modal Alignment and Knowledge Transfer (CAKT) (TOT-CAKT) for ASR. In the TOT-CAKT, local neighboring frames of acoustic sequences are smoothly mapped to neighboring regions of linguistic sequences, preserving their temporal order relationship in feature alignment and matching. With the TOT-CAKT model framework, we conduct Mandarin ASR experiments with a pretrained Chinese PLM for linguistic knowledge transfer. Our results demonstrate that the proposed TOT-CAKT significantly improves ASR performance compared to several state-of-the-art models employing linguistic knowledge transfer, and addresses the weaknesses of the original OT-based method in sequential feature alignment for ASR.

arXiv:2409.02049

Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation

Low-resolution face recognition is a challenging task due to the missing of informative details. Recent approaches based on knowledge distillation have proven that high-resolution clues can well guide low-resolution face recognition via proper knowledge transfer. However, due to the distribution difference between training and testing faces, the learned models often suffer from poor adaptability. To address that, we split the knowledge transfer process into distillation and adaptation steps, and propose an adaptable instance-relation distillation approach to facilitate low-resolution face recognition. In the approach, the student distills knowledge from high-resolution teacher in both instance level and relation level, providing sufficient cross-resolution knowledge transfer. Then, the learned student can be adaptable to recognize low-resolution faces with adaptive batch normalization in inference. In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.

arXiv:2409.01679

Adaptive Explicit Knowledge Transfer for Knowledge Distillation

Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by effectively delivering the probability distribution for the non-target classes from the teacher model, which is known as `implicit (dark) knowledge', to the student model. Through gradient analysis, we first show that this actually has an effect of adaptively controlling the learning of implicit knowledge. Then, we propose a new loss that enables the student to learn explicit knowledge (i.e., the teacher's confidence about the target class) along with implicit knowledge in an adaptive manner. Furthermore, we propose to separate the classification and distillation tasks for effective distillation and inter-class relationship modeling. Experimental results demonstrate that the proposed method, called adaptive explicit knowledge transfer (AEKT) method, achieves improved performance compared to the state-of-the-art KD methods on the CIFAR-100 and ImageNet datasets.

arXiv:2409.02778

Regularized Multi-output Gaussian Convolution Process with Domain Adaptation

Multi-output Gaussian process (MGP) has been attracting increasing attention as a transfer learning method to model multiple outputs. Despite its high flexibility and generality, MGP still faces two critical challenges when applied to transfer learning. The first one is negative transfer, which occurs when there exists no shared information among the outputs. The second challenge is the input domain inconsistency, which is commonly studied in transfer learning yet not explored in MGP. In this paper, we propose a regularized MGP modeling framework with domain adaptation to overcome these challenges. More specifically, a sparse covariance matrix of MGP is proposed by using convolution process, where penalization terms are added to adaptively select the most informative outputs for knowledge transfer. To deal with the domain inconsistency, a domain adaptation method is proposed by marginalizing inconsistent features and expanding missing features to align the input domains among different outputs. Statistical properties of the proposed method are provided to guarantee the performance practically and asymptotically. The proposed framework outperforms state-of-the-art benchmarks in comprehensive simulation studies and one real case study of a ceramic manufacturing process. The results demonstrate the effectiveness of our method in dealing with both the negative transfer and the domain inconsistency.

arXiv:2409.02555

Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations. However, these approaches still face limitations in adapting to the situation where the recognized objects exhibit significant representation discrepancies between training and testing images. In this study, we propose a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition. Our approach enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects. To extract sufficient knowledge, the student learning is supervised with contrastive relational distillation loss, which preserves the similarities in various relational structures in contrastive representation space. In this manner, the capability of recovering missing details of familiar low-resolution objects can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution object classification and low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.

arXiv:2409.02404

Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and strong privacy. In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models. Our key idea is taking models as bridge to distill knowledge from private data and then transfer it to learn a student network via two streams. First, discriminative stream trains a baseline classifier on private data and an ensemble of teachers on multiple disjoint private subsets, respectively. Then, generative stream takes the classifier as a fixed discriminator and trains a generator in a data-free manner. After that, the generator is used to generate massive synthetic data which are further applied to train a variational autoencoder (VAE). Among these synthetic data, a few of them are fed into the teacher ensemble to query labels via differentially private aggregation, while most of them are embedded to the trained VAE for reconstructing synthetic data. Finally, a semi-supervised student learning is performed to simultaneously handle two tasks: knowledge transfer from the teachers with distillation on few privately labeled synthetic data, and knowledge enhancement with tangent-normal adversarial regularization on many triples of reconstructed synthetic data. In this way, our approach can control query cost over private data and mitigate accuracy degradation in a unified manner, leading to a privacy-preserving student model. Extensive experiments and analysis clearly show the effectiveness of the proposed approach.

arXiv:2409.00341공식 코드 · Papers with Code

Aligning Medical Images with General Knowledge from Large Language Models

Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel visual symptom-guided prompt learning framework for medical image analysis, which facilitates general knowledge transfer from CLIP. ViP consists of two key components: a visual symptom generator (VSG) and a dual-prompt network. Specifically, VSG aims to extract explicable visual symptoms from pre-trained large language models, while the dual-prompt network utilizes these visual symptoms to guide the training on two learnable prompt modules, i.e., context prompt and merge prompt, which effectively adapts our framework to medical image analysis via large VLMs. Extensive experimental results demonstrate that ViP can outperform state-of-the-art methods on two challenging datasets.

arXiv:2408.16939공식 코드 · Papers with Code

Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning

Multi-task learning (MTL) is a machine learning paradigm that aims to improve the generalization performance of a model on multiple related tasks by training it simultaneously on those tasks. Unlike MTL, where the model has instant access to the training data of all tasks, continual learning (CL) involves adapting to new sequentially arriving tasks over time without forgetting the previously acquired knowledge. Despite the wide practical adoption of CL and MTL and extensive literature on both areas, there remains a gap in the theoretical understanding of these methods when used with overparameterized models such as deep neural networks. This paper studies the overparameterized linear models as a proxy for more complex models. We develop theoretical results describing the effect of various system parameters on the model's performance in an MTL setup. Specifically, we study the impact of model size, dataset size, and task similarity on the generalization error and knowledge transfer. Additionally, we present theoretical results to characterize the performance of replay-based CL models. Our results reveal the impact of buffer size and model capacity on the forgetting rate in a CL setup and help shed light on some of the state-of-the-art CL methods. Finally, through extensive empirical evaluations, we demonstrate that our theoretical findings are also applicable to deep neural networks, offering valuable guidance for designing MTL and CL models in practice.

arXiv:2408.16800

CNN Based Detection of Cardiovascular Diseases from ECG Images

This study develops a Convolutional Neural Network (CNN) model for detecting myocardial infarction (MI) from Electrocardiogram (ECG) images. The model, built using the InceptionV3 architecture and optimized through transfer learning, was trained using ECG data obtained from the Ch. Pervaiz Elahi Institute of Cardiology in Pakistan. The dataset includes ECG images representing four different cardiac conditions: myocardial infarction, abnormal heartbeat, history of myocardial infarction, and normal heart activity. The developed model successfully detects MI and other cardiovascular conditions with an accuracy of 93.27%. This study demonstrates that deep learning-based models can provide significant support to clinicians in the early detection and prevention of heart attacks.

arXiv:2408.16965공식 코드 · Papers with Code

Contrastive Learning with Synthetic Positives

Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is constrained as the nearest neighbor algorithm primarily identifies ``easy'' positive pairs, where the representations are already closely located in the embedding space. In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional positives to help the model learn from diverse positives. Through feature interpolation in the diffusion model sampling process, we generate images with distinct backgrounds yet similar semantic content to the anchor image. These images are considered ``hard'' positives for the anchor image, and when included as supplementary positives in the contrastive loss, they contribute to a performance improvement of over 2\% and 1\% in linear evaluation compared to the previous NNCLR and All4One methods across multiple benchmark datasets such as CIFAR10, achieving state-of-the-art methods. On transfer learning benchmarks, CLSP outperforms existing SSL frameworks on 6 out of 8 downstream datasets. We believe CLSP establishes a valuable baseline for future SSL studies incorporating synthetic data in the training process.

arXiv:2408.16947

An Empirical Study of Scaling Laws for Transfer

We present a limited empirical study of scaling laws for transfer learning in transformer models. More specifically, we examine a scaling law that incorporates a "transfer gap" term, indicating the effectiveness of pre-training on one distribution when optimizing for downstream performance on another distribution. When the transfer gap is low, pre-training is a cost-effective strategy for improving downstream performance. Conversely, when the gap is high, collecting high-quality fine-tuning data becomes relatively more cost effective. Fitting the scaling law to experiments from diverse datasets reveals significant variations in the transfer gap across distributions. In theory, the scaling law can inform optimal data allocation strategies and highlights how the scarcity of downstream data can bottleneck performance. Our findings contribute to a principled way to measure transfer learning efficiency and understand how data availability affects capabilities.

arXiv:2408.16859공식 코드 · Papers with Code

Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study

This study evaluates the effectiveness of deep learning models in classifying histopathological images for early and accurate detection of breast cancer. Eight advanced models, including ResNet-50, DenseNet-121, ResNeXt-50, Vision Transformer (ViT), GoogLeNet (Inception v3), EfficientNet, MobileNet, and SqueezeNet, were compared using a dataset of 277,524 image patches. The Vision Transformer (ViT) model, with its attention-based mechanisms, achieved the highest validation accuracy of 94%, outperforming conventional CNNs. The study demonstrates the potential of advanced machine learning methods to enhance precision and efficiency in breast cancer diagnosis in clinical settings.

arXiv:2408.17011

Disease Classification and Impact of Pretrained Deep Convolution Neural Networks on Diverse Medical Imaging Datasets across Imaging Modalities

Imaging techniques such as Chest X-rays, whole slide images, and optical coherence tomography serve as the initial screening and detection for a wide variety of medical pulmonary and ophthalmic conditions respectively. This paper investigates the intricacies of using pretrained deep convolutional neural networks with transfer learning across diverse medical imaging datasets with varying modalities for binary and multiclass classification. We conducted a comprehensive performance analysis with ten network architectures and model families each with pretraining and random initialization. Our finding showed that the use of pretrained models as fixed feature extractors yields poor performance irrespective of the datasets. Contrary, histopathology microscopy whole slide images have better performance. It is also found that deeper and more complex architectures did not necessarily result in the best performance. This observation implies that the improvements in ImageNet are not parallel to the medical imaging tasks. Within a medical domain, the performance of the network architectures varies within model families with shifts in datasets. This indicates that the performance of models within a specific modality may not be conclusive for another modality within the same domain. This study provides a deeper understanding of the applications of deep learning techniques in medical imaging and highlights the impact of pretrained networks across different medical imaging datasets under five different experimental settings.

arXiv:2408.16401

On Transfer Learning for a Fully Convolutional Deep Neural SIMO Receiver

Deep learning has been used to tackle problems in wireless communication including signal detection, channel estimation, traffic prediction, and demapping. Achieving reasonable results with deep learning typically requires large datasets which may be difficult to obtain for every scenario/configuration in wireless communication. Transfer learning (TL) solves this problem by leveraging knowledge and experience gained from one scenario or configuration to adapt a system to a different scenario using smaller dataset. TL has been studied for various stand-alone parts of the radio receiver where individual receiver components, for example, the channel estimator are replaced by a neural network. There has however been no work on TL for receivers where the entire receiver chain is replaced by a neural network. This paper fills this gap by studying the performance of fine-tuning based transfer learning techniques for various configuration mismatch cases using a deep neural single-input-multiple-output(SIMO) receiver. Simulation results show that overall, partial fine-tuning better closes the performance gap between zero target dataset and sufficient target dataset.

arXiv:2408.13270

Efficient Task Transfer for HLS DSE

There have been several recent works proposed to utilize model-based optimization methods to improve the productivity of using high-level synthesis (HLS) to design domain-specific architectures. They would replace the time-consuming performance estimation or simulation of design with a proxy model, and automatically insert pragmas to guide hardware optimizations. In this work, we address the challenges associated with high-level synthesis (HLS) design space exploration (DSE) through the evolving landscape of HLS tools. As these tools develop, the quality of results (QoR) from synthesis can vary significantly, complicating the maintenance of optimal design strategies across different toolchains. We introduce Active-CEM, a task transfer learning scheme that leverages a model-based explorer designed to adapt efficiently to changes in toolchains. This approach optimizes sample efficiency by identifying high-quality design configurations under a new toolchain without requiring extensive re-evaluation. We further refine our methodology by incorporating toolchain-invariant modeling. This allows us to predict QoR changes more accurately despite shifts in the black-box implementation of the toolchains. Experiment results on the HLSyn benchmark transitioning to new toolchain show an average performance improvement of 1.58$\times$ compared to AutoDSE and a 1.2$\times$ improvement over HARP, while also increasing the sample efficiency by 5.26$\times$, and reducing the runtime by 2.7$\times$.

arXiv:2408.16238

Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction

Natural content and advertisement coexist in industrial recommendation systems but differ in data distribution. Concretely, traffic related to the advertisement is considerably sparser compared to that of natural content, which motivates the development of transferring knowledge from the richer source natural content domain to the sparser advertising domain. The challenges include the inefficiencies arising from the management of extensive source data and the problem of 'catastrophic forgetting' that results from the CTR model's daily updating. To this end, we propose a novel tri-level asynchronous framework, i.e., Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction (E-CDCTR), to transfer comprehensive knowledge of natural content to advertisement CTR models. This framework consists of three key components: Tiny Pre-training Model ((TPM), which trains a tiny CTR model with several basic features on long-term natural data; Complete Pre-training Model (CPM), which trains a CTR model holding network structure and input features the same as target advertisement on short-term natural data; Advertisement CTR model (A-CTR), which derives its parameter initialization from CPM together with multiple historical embeddings from TPM as extra feature and then fine-tunes on advertisement data. TPM provides richer representations of user and item for both the CPM and A-CTR, effectively alleviating the forgetting problem inherent in the daily updates. CPM further enhances the advertisement model by providing knowledgeable initialization, thereby alleviating the data sparsity challenges typically encountered by advertising CTR models. Such a tri-level cross-domain transfer learning framework offers an efficient solution to address both data sparsity and `catastrophic forgetting', yielding remarkable improvements.

arXiv:2408.16749

Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge

The United States has experienced a significant increase in violent extremism, prompting the need for automated tools to detect and limit the spread of extremist ideology online. This study evaluates the performance of Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformers (GPT) in detecting and classifying online domestic extremist posts. We collected social media posts containing "far-right" and "far-left" ideological keywords and manually labeled them as extremist or non-extremist. Extremist posts were further classified into one or more of five contributing elements of extremism based on a working definitional framework. The BERT model's performance was evaluated based on training data size and knowledge transfer between categories. We also compared the performance of GPT 3.5 and GPT 4 models using different prompts: na\"ive, layperson-definition, role-playing, and professional-definition. Results showed that the best performing GPT models outperformed the best performing BERT models, with more detailed prompts generally yielding better results. However, overly complex prompts may impair performance. Different versions of GPT have unique sensitives to what they consider extremist. GPT 3.5 performed better at classifying far-left extremist posts, while GPT 4 performed better at classifying far-right extremist posts. Large language models, represented by GPT models, hold significant potential for online extremism classification tasks, surpassing traditional BERT models in a zero-shot setting. Future research should explore human-computer interactions in optimizing GPT models for extremist detection and classification tasks to develop more efficient (e.g., quicker, less effort) and effective (e.g., fewer errors or mistakes) methods for identifying extremist content.

arXiv:2408.16189

Adaptive Sample Aggregation In Transfer Learning

Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address this problem, each driven by one of a multitude of possible divergence measures between source and target distributions. A first question asked in this work is whether there exist unified algorithmic approaches that automatically adapt to many of these divergence measures simultaneously. We show that this is indeed the case for a large family of divergences proposed across classification and regression tasks, as they all happen to upper-bound the same measure of continuity between source and target risks, which we refer to as a weak modulus of transfer. This more unified view allows us, first, to identify algorithmic approaches that are simultaneously adaptive to these various divergence measures via a reduction to particular confidence sets. Second, it allows for a more refined understanding of the statistical limits of transfer under such divergences, and in particular, reveals regimes with faster rates than might be expected under coarser lenses. We then turn to situations that are not well captured by the weak modulus and corresponding divergences: these are situations where the aggregate of source and target data can improve target performance significantly beyond what's possible with either source or target data alone. We show that common such situations -- as may arise, e.g., under certain causal models with spurious correlations -- are well described by a so-called strong modulus of transfer which supersedes the weak modulus. We finally show that the strong modulus also admits adaptive procedures, which achieve near optimal rates in terms of the unknown strong modulus, and therefore apply in more general settings.

논문 ID: document/1043670

Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces

Domain adaptation has gained significant attention to address the nonstationarity problem in electroencephalography (EEG) data in motor imagery (MI) classification. In MI classification, domain adaptation addresses cross-session variations, enhancing the classifier’s generalization capabilities. However, the existing methods have struggled to effectively capture both temporal and spatial features, resulting in limited classification accuracy. To tackle this issue, we propose the multiview adversarial contrastive network (MACNet). The proposed MACNet simultaneously learns spatial and temporal features in two different views: Euclidean and Riemannian. Furthermore, we introduce a multilevel domain mix-up technique to enhance domain alignment at both signal and embedding levels. The proposed MACNet method is evaluated on three public datasets. It achieves an accuracy of 83.79% on the BCI Competition IV dataset, 80.00% on the open source brain-machine interface (OpenBMI) dataset, and 85.83% on the sensorimotor rthythms (SMR) dataset that outperforms previous methods in cross-session transfer learning.

arXiv:2408.16612

Data Quality Monitoring through Transfer Learning on Anomaly Detection for the Hadron Calorimeters

The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains for various purposes, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of AD for the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. We have transferred the ST AD models trained on data collected from one part of a calorimeter to another. We have investigated different configurations of TL on semi-supervised autoencoders of the ST AD models -- transferring convolutional, graph, and recurrent neural networks of both the encoder and decoder networks. The experiment results demonstrate that TL effectively enhances the model learning accuracy on a target subdetector. The TL achieves promising data reconstruction and AD performance while substantially reducing the trainable parameters of the AD models. It also improves robustness against anomaly contamination in the training data sets of the semi-supervised AD models.