The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the combination of global and local feature information. This paper proposes a multi-network contrastive learning framework based on global and local representations. We introduce global and local feature information for self-supervised contrastive learning through multiple networks. The model learns feature information at different scales of an image by contrasting the embedding pairs generated by multiple networks. The framework also expands the number of samples used for contrast and improves the training efficiency of the model. Linear evaluation results on three benchmark datasets show that our method outperforms several existing classical self-supervised learning methods.
相關內容
Despite the promising results of machine learning models in malware detection, they face the problem of concept drift due to malware constant evolution. This leads to a decline in performance over time, as the data distribution of the new files differs from the training one, requiring regular model update. In this work, we propose a model-agnostic protocol to improve a baseline neural network to handle with the drift problem. We show the importance of feature reduction and training with the most recent validation set possible, and propose a loss function named Drift-Resilient Binary Cross-Entropy, an improvement to the classical Binary Cross-Entropy more effective against drift. We train our model on the EMBER dataset (2018) and evaluate it on a dataset of recent malicious files, collected between 2020 and 2023. Our improved model shows promising results, detecting 15.2% more malware than a baseline model.
We present a method for learning multiple scene representations given a small labeled set, by exploiting the relationships between such representations in the form of a multi-task hypergraph. We also show how we can use the hypergraph to improve a powerful pretrained VisTransformer model without any additional labeled data. In our hypergraph, each node is an interpretation layer (e.g., depth or segmentation) of the scene. Within each hyperedge, one or several input nodes predict the layer at the output node. Thus, each node could be an input node in some hyperedges and an output node in others. In this way, multiple paths can reach the same node, to form ensembles from which we obtain robust pseudolabels, which allow self-supervised learning in the hypergraph. We test different ensemble models and different types of hyperedges and show superior performance to other multi-task graph models in the field. We also introduce Dronescapes, a large video dataset captured with UAVs in different complex real-world scenes, with multiple representations, suitable for multi-task learning.
Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and Q-learning, providing details regarding the INFORMS APS inaugural Applied Probability Trust Plenary Lecture, presented in Nancy France, June 2023. The paper also presents new approaches to ensure stability and potentially accelerated convergence for these algorithms, and stochastic approximation in other settings. Two contributions are entirely new: 1. Stability of Q-learning with linear function approximation has been an open topic for research for over three decades. It is shown that with appropriate optimistic training in the form of a modified Gibbs policy, there exists a solution to the projected Bellman equation, and the algorithm is stable (in terms of bounded parameter estimates). Convergence remains one of many open topics for research. 2. The new Zap Zero algorithm is designed to approximate the Newton-Raphson flow without matrix inversion. It is stable and convergent under mild assumptions on the mean flow vector field for the algorithm, and compatible statistical assumption on an underlying Markov chain. The algorithm is a general approach to stochastic approximation which in particular applies to Q-learning with "oblivious" training even with non-linear function approximation.
Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer from noise present in inputs leading to erroneous predictions. While it is possible to enhance models through retraining/fine-tuning, this is not a once-and-for-all approach and incurs significant overhead. In particular, these techniques cannot on-the-fly improve performance of (deployed) models. There are currently some techniques for input denoising in other domains (such as image processing), but since code input is discrete and must strictly abide by complex syntactic and semantic constraints, input denoising techniques in other fields are almost not applicable. In this work, we propose the first input denoising technique (i.e., CodeDenoise) for deep code models. Its key idea is to localize noisy identifiers in (likely) mispredicted inputs, and denoise such inputs by cleansing the located identifiers. It does not need to retrain or reconstruct the model, but only needs to cleanse inputs on-the-fly to improve performance. Our experiments on 18 deep code models (i.e., three pre-trained models with six code-based datasets) demonstrate the effectiveness and efficiency of CodeDenoise. For example, on average, CodeDenoise successfully denoises 21.91% of mispredicted inputs and improves the original models by 2.04% in terms of the model accuracy across all the subjects in an average of 0.48 second spent on each input, substantially outperforming the widely-used fine-tuning strategy.
With the success of self-supervised learning, multimodal foundation models have rapidly adapted a wide range of downstream tasks driven by vision and language (VL) pretraining. State-of-the-art methods achieve impressive performance by pre-training on large-scale datasets. However, bridging the semantic gap between the two modalities remains a nonnegligible challenge for VL tasks. In this work, we propose an efficient computation framework for multimodal alignment by introducing a novel visual semantic module to further improve the performance of the VL tasks. Specifically, we propose a flexible model, namely Artificial-Spiking Hierarchical Networks (ASH-Nets), which combines the complementary advantages of Artificial neural networks (ANNs) and Spiking neural networks (SNNs) to enrich visual semantic representations. In particular, a visual concrete encoder and a semantic abstract encoder are constructed to learn continuous and discrete latent variables to enhance the flexibility of semantic encoding. Considering the spatio-temporal properties of SNNs modeling, we introduce a contrastive learning method to optimize the inputs of similar samples. This can improve the computational efficiency of the hierarchical network, while the augmentation of hard samples is beneficial to the learning of visual representations. Furthermore, the Spiking to Text Uni-Alignment Learning (STUA) pre-training method is proposed, which only relies on text features to enhance the encoding ability of abstract semantics. We validate the performance on multiple well-established downstream VL tasks. Experiments show that the proposed ASH-Nets achieve competitive results.
Deep learning has made significant strides in video understanding tasks, but the computation required to classify lengthy and massive videos using clip-level video classifiers remains impractical and prohibitively expensive. To address this issue, we propose Audio-Visual Glance Network (AVGN), which leverages the commonly available audio and visual modalities to efficiently process the spatio-temporally important parts of a video. AVGN firstly divides the video into snippets of image-audio clip pair and employs lightweight unimodal encoders to extract global visual features and audio features. To identify the important temporal segments, we use an Audio-Visual Temporal Saliency Transformer (AV-TeST) that estimates the saliency scores of each frame. To further increase efficiency in the spatial dimension, AVGN processes only the important patches instead of the whole images. We use an Audio-Enhanced Spatial Patch Attention (AESPA) module to produce a set of enhanced coarse visual features, which are fed to a policy network that produces the coordinates of the important patches. This approach enables us to focus only on the most important spatio-temporally parts of the video, leading to more efficient video recognition. Moreover, we incorporate various training techniques and multi-modal feature fusion to enhance the robustness and effectiveness of our AVGN. By combining these strategies, our AVGN sets new state-of-the-art performance in multiple video recognition benchmarks while achieving faster processing speed.
Deep learning-based surrogate models have been widely applied in geological carbon storage (GCS) problems to accelerate the prediction of reservoir pressure and CO2 plume migration. Large amounts of data from physics-based numerical simulators are required to train a model to accurately predict the complex physical behaviors associated with this process. In practice, the available training data are always limited in large-scale 3D problems due to the high computational cost. Therefore, we propose to use a multi-fidelity Fourier Neural Operator to solve large-scale GCS problems with more affordable multi-fidelity training datasets. The Fourier Neural Operator has a desirable grid-invariant property, which simplifies the transfer learning procedure between datasets with different discretization. We first test the model efficacy on a GCS reservoir model being discretized into 110k grid cells. The multi-fidelity model can predict with accuracy comparable to a high-fidelity model trained with the same amount of high-fidelity data with 81% less data generation costs. We further test the generalizability of the multi-fidelity model on a same reservoir model with a finer discretization of 1 million grid cells. This case was made more challenging by employing high-fidelity and low-fidelity datasets generated by different geostatistical models and reservoir simulators. We observe that the multi-fidelity FNO model can predict pressure fields with reasonable accuracy even when the high-fidelity data are extremely limited.
Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of large pre-trained models efficiently and reduce their complexity. In this work, we study a challenging low resource conversational telephony speech corpus from the medical domain in Vietnamese and German. We show the benefits of using unsupervised techniques beyond simple fine-tuning of large pre-trained models, discuss how to adapt them to a practical telephony task including bandwidth transfer and investigate different data conditions for pre-training and fine-tuning. We outperform the project baselines by 22% relative using pretraining techniques. Further gains of 29% can be achieved by refinements of architecture and training and 6% by adding 0.8 h of in-domain adaptation data.
Over the past decade, domain adaptation has become a widely studied branch of transfer learning that aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access to both source and target domain data simultaneously, which may not be feasible in real-world scenarios due to privacy and confidentiality concerns. As a result, the research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years, which only utilizes the source-trained model and unlabeled target data to adapt to the target domain. Despite the rapid explosion of SFDA work, yet there has no timely and comprehensive survey in the field. To fill this gap, we provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme based on the framework of transfer learning. Instead of presenting each approach independently, we modularize several components of each method to more clearly illustrate their relationships and mechanics in light of the composite properties of each method. Furthermore, we compare the results of more than 30 representative SFDA methods on three popular classification benchmarks, namely Office-31, Office-home, and VisDA, to explore the effectiveness of various technical routes and the combination effects among them. Additionally, we briefly introduce the applications of SFDA and related fields. Drawing from our analysis of the challenges facing SFDA, we offer some insights into future research directions and potential settings.
While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the snippet level (a phrase or sentence). Factorization Machine provides a possible approach to learning element-wise interaction for recommender systems, but they are not directly applicable to our task due to the inability to model contexts and word sequences. In this work, we develop two Position-aware Factorization Machines which consider word interaction, context and position information. Such information is jointly encoded in a set of sentiment-oriented word interaction vectors. Compared to traditional word embeddings, SWI vectors explicitly capture sentiment-oriented word interaction and simplify the parameter learning. Experimental results show that while they have comparable performance with state-of-the-art methods for document-level classification, they benefit the snippet/sentence-level sentiment analysis.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191