The convolutional neural network (CNN) and transformer are two of the most widely implemented models in the computer vision field. However, the former (latter) one mainly captures local (global) features only. To address the limitation in model performance caused by the lack of features, we develop a novel classification network CECT by controllable ensemble CNN and transformer. CECT is composed of a convolutional encoder block, a transposed-convolutional decoder block, and a transformer classification block. Different from existing methods, our CECT can capture features at both multi-local and global scales without any bells and whistles. Moreover, the contribution of local features at different scales can be controlled with the proposed ensemble coefficients. We evaluate CECT on two public COVID-19 datasets and it outperforms existing state-of-the-art methods. With remarkable feature capture ability, we believe CECT can be extended to other medical image classification scenarios as a diagnosis assistant. Code is available at //github.com/NUS-Tim/CECT.
相關內容
Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complexity, some models present limitations, such as the assumption of Markovian traffic in queuing theory models, or the high computational cost of network simulators. Recent advances in machine learning, such as Graph Neural Networks (GNN), are enabling a new generation of network models that are data-driven and can learn complex non-linear behaviors. In this paper, we present RouteNet-Fermi, a custom GNN model that shares the same goals as Queuing Theory, while being considerably more accurate in the presence of realistic traffic models. The proposed model predicts accurately the delay, jitter, and packet loss of a network. We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles -- e.g., with complex non-Markovian models -- and arbitrary routing and queue scheduling configurations. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators and scales accurately to larger networks. Our model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset of 1,000 samples, including network topologies one order of magnitude larger than those seen during training. Finally, we have also evaluated RouteNet-Fermi with measurements from a physical testbed and packet traces from a real-life network.
Capsule Network is powerful at defining the positional relationship between features in deep neural networks for visual recognition tasks, but it is computationally expensive and not suitable for running on mobile devices. The bottleneck is in the computational complexity of the Dynamic Routing mechanism used between the capsules. On the other hand, XNOR-Net is fast and computationally efficient, though it suffers from low accuracy due to information loss in the binarization process. To address the computational burdens of the Dynamic Routing mechanism, this paper proposes new Fully Connected (FC) layers by xnorizing the linear projection outside or inside the Dynamic Routing within the CapsFC layer. Specifically, our proposed FC layers have two versions, XnODR (Xnorize the Linear Projection Outside Dynamic Routing) and XnIDR (Xnorize the Linear Projection Inside Dynamic Routing). To test the generalization of both XnODR and XnIDR, we insert them into two different networks, MobileNetV2 and ResNet-50. Our experiments on three datasets, MNIST, CIFAR-10, and MultiMNIST validate their effectiveness. The results demonstrate that both XnODR and XnIDR help networks to have high accuracy with lower FLOPs and fewer parameters (e.g., 96.14% correctness with 2.99M parameters and 311.74M FLOPs on CIFAR-10).
Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1% of extra parameters could surpass full fine-tuning in low-data resource scenarios. However, these methods overlook the task-specific information when fine-tuning diverse downstream tasks. In this paper, we propose a simple yet effective method called "Salient Channel Tuning" (SCT) to leverage the task-specific information by forwarding the model with the task images to select partial channels in a feature map that enables us to tune only 1/8 channels leading to significantly lower parameter costs. Experiments outperform full fine-tuning on 18 out of 19 tasks in the VTAB-1K benchmark by adding only 0.11M parameters of the ViT-B, which is 780$\times$ fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot learning surpass other PEFT methods with lower parameter costs, demonstrating our proposed tuning technique's strong capability and effectiveness in the low-data regime.
Ultra-massive multiple-input multiple-output (UM-MIMO) is a cutting-edge technology that promises to revolutionize wireless networks by providing an unprecedentedly high spectral and energy efficiency. The enlarged array aperture of UM-MIMO facilitates the accessibility of the near-field region, thereby offering a novel degree of freedom for communications and sensing. Nevertheless, the transceiver design for such systems is challenging because of the enormous system scale, the complicated channel characteristics, and the uncertainties in propagation environments. Therefore, it is critical to study scalable, low-complexity, and robust algorithms that can efficiently characterize and leverage the properties of the near-field channel. In this article, we will advocate two general frameworks from an artificial intelligence (AI)-native perspective, which are tailored for the algorithmic design of near-field UM-MIMO transceivers. Specifically, the frameworks for both iterative and non-iterative algorithms are discussed. Near-field beam focusing and channel estimation are presented as two tutorial-style examples to demonstrate the significant advantages of the proposed AI-native frameworks in terms of various key performance indicators.
One key bottleneck of employing state-of-the-art semantic segmentation networks in the real world is the availability of training labels. Conventional semantic segmentation networks require massive pixel-wise annotated labels to reach state-of-the-art prediction quality. Hence, several works focus on semantic segmentation networks trained with only image-level annotations. However, when scrutinizing the results of state-of-the-art in more detail, we notice that they are remarkably close to each other on average prediction quality, different approaches perform better in different classes while providing low quality in others. To address this problem, we propose a novel framework, ISLE, which employs an ensemble of the "pseudo-labels" for a given set of different semantic segmentation techniques on a class-wise level. Pseudo-labels are the pixel-wise predictions of the image-level semantic segmentation frameworks used to train the final segmentation model. Our pseudo-labels seamlessly combine the strong points of multiple segmentation techniques approaches to reach superior prediction quality. We reach up to 2.4% improvement over ISLE's individual components. An exhaustive analysis was performed to demonstrate ISLE's effectiveness over state-of-the-art frameworks for image-level semantic segmentation.
Video saliency prediction and detection are thriving research domains that enable computers to simulate the distribution of visual attention akin to how humans perceiving dynamic scenes. While many approaches have crafted task-specific training paradigms for either video saliency prediction or video salient object detection tasks, few attention has been devoted to devising a generalized saliency modeling framework that seamlessly bridges both these distinct tasks. In this study, we introduce the Unified Saliency Transformer (UniST) framework, which comprehensively utilizes the essential attributes of video saliency prediction and video salient object detection. In addition to extracting representations of frame sequences, a saliency-aware transformer is designed to learn the spatio-temporal representations at progressively increased resolutions, while incorporating effective cross-scale saliency information to produce a robust representation. Furthermore, a task-specific decoder is proposed to perform the final prediction for each task. To the best of our knowledge, this is the first work that explores designing a transformer structure for both saliency modeling tasks. Convincible experiments demonstrate that the proposed UniST achieves superior performance across seven challenging benchmarks for two tasks, and significantly outperforms the other state-of-the-art methods.
The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications. However, federated graph learning (FGL), even though graph data are prevalent, has not been well supported due to its unique characteristics and requirements. The lack of FGL-related framework increases the efforts for accomplishing reproducible research and deploying in real-world applications. Motivated by such strong demand, in this paper, we first discuss the challenges in creating an easy-to-use FGL package and accordingly present our implemented package FederatedScope-GNN (FS-G), which provides (1) a unified view for modularizing and expressing FGL algorithms; (2) comprehensive DataZoo and ModelZoo for out-of-the-box FGL capability; (3) an efficient model auto-tuning component; and (4) off-the-shelf privacy attack and defense abilities. We validate the effectiveness of FS-G by conducting extensive experiments, which simultaneously gains many valuable insights about FGL for the community. Moreover, we employ FS-G to serve the FGL application in real-world E-commerce scenarios, where the attained improvements indicate great potential business benefits. We publicly release FS-G, as submodules of FederatedScope, at //github.com/alibaba/FederatedScope to promote FGL's research and enable broad applications that would otherwise be infeasible due to the lack of a dedicated package.
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-selected design are threefold: (1) NesT converges faster and requires much less training data to achieve good generalization on both ImageNet and small datasets like CIFAR; (2) when extending our key ideas to image generation, NesT leads to a strong decoder that is 8$\times$ faster than previous transformer-based generators; and (3) we show that decoupling the feature learning and abstraction processes via this nested hierarchy in our design enables constructing a novel method (named GradCAT) for visually interpreting the learned model. Source code is available //github.com/google-research/nested-transformer.
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance. In this paper, we attempt to acquire both efficiency and effectiveness simultaneously. First of all, besides traditionally treating H x W x T video frames as space-time signal (viewing from the Height-Width spatial plane), we propose to also model video from the other two Height-Time and Width-Time planes, to capture the dynamics of video thoroughly. Secondly, our model is designed based on 2D CNN backbones and model complexity is well kept in mind by design. Specifically, we introduce a novel multi-view fusion (MVF) module to exploit video dynamics using separable convolution for efficiency. It is a plug-and-play module and can be inserted into off-the-shelf 2D CNNs to form a simple yet effective model called MVFNet. Moreover, MVFNet can be thought of as a generalized video modeling framework and it can specialize to be existing methods such as C2D, SlowOnly, and TSM under different settings. Extensive experiments are conducted on popular benchmarks (i.e., Something-Something V1 & V2, Kinetics, UCF-101, and HMDB-51) to show its superiority. The proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.
A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. Specifically, MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Extensive experiments on three real-world heterogeneous graph datasets for node classification, node clustering, and link prediction show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191