注意力机制已成为现代卷积神经网络（CNNs）的重要组成部分，通过最小的计算开销带来显著的性能提升。然而，不同通道注意力设计的效率与精度的权衡仍处于探索阶段。本文通过在CIFAR 10数据集上对ResNet 18和MobileNetV2架构进行实证研究，比较了Squeeze and Excitation（SE）、Efficient Channel Attention（ECA）以及所提出的Lite Channel Attention（LCA）模块。LCA采用自适应的一维卷积和分组操作来减少参数使用，同时保持有效的注意力行为。实验结果表明，LCA在ResNet 18上达到94.68%的准确率，在MobileNetV2上达到93.10%的准确率，同时在参数效率方面与ECA相当，并保持了有利的推理延迟。全面的基准测试包括FLOPs、参数计数和GPU延迟测量，为在资源受限环境中部署增强注意力的CNNs提供了实用见解。
英文摘要：
Attention mechanisms have become integral to modern convolutional neural networks (CNNs), delivering notable performance improvements with minimal computational overhead. However, the efficiency accuracy trade off of different channel attention designs remains underexplored. This work presents an empirical study comparing Squeeze and Excitation (SE), Efficient Channel Attention (ECA), and a proposed Lite Channel Attention (LCA) module across ResNet 18 and MobileNetV2 architectures on CIFAR 10. LCA employs adaptive one dimensional convolutions with grouped operations to reduce parameter usage while preserving effective attention behavior. Experimental results show that LCA achieves competitive accuracy, reaching 94.68 percent on ResNet 18 and 93.10 percent on MobileNetV2, while matching ECA in parameter efficiency and maintaining favorable inference latency. Comprehensive benchmarks including FLOPs, parameter counts, and GPU latency measurements are provided, offering practical insights for deploying attention enhanced CNNs in resource constrained environments.
Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI（达勒莫勒人工智能研究所 (IDSIA), 卢加诺大学-瑞士南部应用科学与艺术大学）；ETH Zürich（苏黎世联邦理工学院）；University of Bonn（波恩大学）
We consider the task of visually estimating the pose of a human from images acquired by a nearby nano-drone; in this context, we propose a data augmentation approach based on synthetic background substitution to learn a lightweight CNN model from a small real-world training set. Experimental results on data from two different labs proves that the approach improves generalization to unseen environments.
The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤集团有限公司）；Nanyang Technological University（南洋理工大学）
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context, these models often fail in challenging scenarios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps extracted from a model…
Human activity recognition (HAR) is a machine learning task with important applications in healthcare especially in the context of home care of patients and older adults. HAR is often based on data collected from smart sensors, particularly smart home IoT devices such as smartphones, wearables and other body sensors. Deep learning techniques like convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been used for HAR, both in centralized and federated settings. However, these techniques have certain limitations: RNNs cannot be easily parallelized, CNNs have the limitat…
Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
Faculty of Computing, Sabaragamuwa University of Sri Lanka（斯里兰卡萨巴拉加穆瓦大学计算机学院）；Faculty of Engineering, University of Moratuwa（莫拉图瓦大学工程学院）；School of Computing Technologies, RMIT University（RMIT大学计算技术学院）；School of Engineering & Digital Technologies, University of Southern Queensland（南昆士兰大学工程与数字技术学院）；School of Engineering & Technologies, UNSW（新南威尔士大学工程与技术学院）；Faculty of Science and Technology, Charles Darwin University（查尔斯达尔文大学科学技术学院）
Convolutional Neural Networks (CNNs) are being increasingly used to address the problem of iris presentation attack detection. In this work, we propose attention-guided iris presentation attack detection (AG-PAD) to augment CNNs with attention mechanisms. Two types of attention modules are independently appended on top of the last convolutional layer of the backbone network. Specifically, the channel attention module is used to model the inter-channel relationship between features, while the position attention module is used to model inter-spatial relationship between features. An element-wise…
Land-cover classification has long been a hot and difficult challenge in remote sensing community. With massive High-resolution Remote Sensing (HRS) images available, manually and automatically designed Convolutional Neural Networks (CNNs) have already shown their great latent capacity on HRS land-cover classification in recent years. Especially, the former can achieve better performance while the latter is able to generate lightweight architecture. Unfortunately, they both have shortcomings. On the one hand, because manual CNNs are almost proposed for natural image processing, it becomes very…
Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build the standard Chinese herbs datasets firstly. According to the characteristics of herbal images, we proposed the competitive attentional fusion pyramid networks to model the features of herbal image, which mdoels the relationship of feature maps from different levels, and re-weights multi-level channels with channel-wise attention mechanism. In this way, we can dynamically adjust the weight of feature maps from various …
National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）
Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our network architecture allows us to obtain an attention mask for each feature while existing CNN visualization methods provide only a common attention mask for all features. We apply the proposed multi-channel attention mechanism to multi-attribute recognition task. We can obtain different attention mask for each feature and for each attribute. Those analyses …
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of New South Wales（新南威尔士大学）；Amazon（亚马逊）
3D convolution neural networks (CNNs) have been the prevailing option for video recognition. To capture the temporal information, 3D convolutions are computed along the sequences, leading to cubically growing and expensive computations. To reduce the computational cost, previous methods resort to manually designed 3D/2D CNN structures with approximations or automatic search, which sacrifice the modeling ability or make training time-consuming. In this work, we propose to automatically design efficient 3D CNN architectures via a novel training-free neural architecture search approach tailored f…
University of Essex（埃塞克斯大学）；ETH Zurich（苏黎世联邦理工学院）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Queensland University of Technology（昆士兰科技大学）
This paper presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12x average speedup relative to state-of-the-art methods.
University of Stuttgart（斯图加特大学）；University of Houston（休斯顿大学）
Blind inpainting algorithms based on deep learning architectures have shown a remarkable performance in recent years, typically outperforming model-based methods both in terms of image quality and run time. However, neural network strategies typically lack a theoretical explanation, which contrasts with the well-understood theory underlying model-based methods. In this work, we leverage the advantages of both approaches by integrating theoretically founded concepts from transform domain methods and sparse approximations into a CNN-based approach for blind image inpainting. To this end, we pres…
University of Essex（埃塞克斯大学）；Queensland University of Technology（昆士兰科技大学）
In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art (SOTA) performance for Visual Place Recognition (VPR), a pivotal component of long-term intelligent robotic vision (vision-aware localization and navigation systems). The prestigious generalization power of D-CNNs gained upon training on large scale places datasets and learned persistent image regions which are found to be robust for specific place recognition under changing conditions and camera viewpoints. However, against the computation and power intensive D-CNNs based VPR algorithms that are emp…
Transformer-based models, such as the Vision Transformer (ViT), can outperform onvolutional Neural Networks (CNNs) in some vision tasks when there is sufficient training data. However, (CNNs) have a strong and useful inductive bias for vision tasks (i.e. translation equivariance and locality). In this work, we developed a novel model architecture that we call a Mobile fish landmark detection network (MFLD-net). We have made this model using convolution operations based on ViT (i.e. Patch embeddings, Multi-Layer Perceptrons). MFLD-net can achieve competitive or better results in low data regime…
Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily operate in a feedforward bottom-up manner. Consequently, the attention mechanism strongly depends on the local information of a single input feature map and does not incorporate relatively semantically-richer contextual information available at higher layers that can specify "what and where to look" in lower-level feature maps through top-down information flow…
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis
Department of Computer Science and Artificial Intelligence（计算机科学与人工智能系）；Division of Electronics and Electrical Engineering（电子与电气工程系）；Dongguk University（东国大学）
HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
University of Technology Sydney（悉尼科技大学）；Nanjing University（南京大学）；Honor Device Company, Ltd（荣耀设备有限公司）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Key Laboratory of Artificial Intelligence, Ministry of Education（教育部人工智能重点实验室）
The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. Unlike convolution operators, self-attention offers infinite receptive field and enables compute-efficient modeling of global dependencies. However, the existing state-of-the-art attention mechanisms incur high compute and/or parameter overheads, and hence unfit for compact convolutional neural networks (CNNs). In this work, we propose a simple yet effective "Ultra-Lightweight Subspace Attention Mechanism" (ULSAM), which infers different attention maps for each fe…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University College London（伦敦大学学院）
Image quality assessment (IQA) algorithm aims to quantify the human perception of image quality. Unfortunately, there is a performance drop when assessing the distortion images generated by generative adversarial network (GAN) with seemingly realistic texture. In this work, we conjecture that this maladaptation lies in the backbone of IQA models, where patch-level prediction methods use independent image patches as input to calculate their scores separately, but lack spatial relationship modeling among image patches. Therefore, we propose an Attention-based Hybrid Image Quality Assessment Netw…
The Chinese University of Hong Kong（香港中文大学）；Samsung AI Cambridge（三星剑桥人工智能中心）；Queen Mary University of London（伦敦玛丽女王大学）
Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer vision. Despite increasingly stronger variants with ever-higher recognition accuracies, due to the quadratic complexity of self-attention, existing ViTs are typically demanding in computation and model size. Although several successful design choices (e.g., the convolutions and hierarchical multi-stage structure) of prior CNNs have been reintroduced into recent ViTs, they are still not sufficient to meet the limited resou…
Center for Theoretical Neuroscience（理论神经科学中心）；Department of Neuroscience（神经科学系）；Columbia University（哥伦比亚大学）
Convolutional neural networks (CNNs) have proven effective for image processing tasks, such as object recognition and classification. Recently, CNNs have been enhanced with concepts of attention, similar to those found in biology. Much of this work on attention has focused on effective serial spatial processing. In this paper, I introduce a simple procedure for applying feature-based attention (FBA) to CNNs and compare multiple implementation options. FBA is a top-down signal applied globally to an input image which aides in detecting chosen objects in cluttered or noisy settings. The concept …
Nanjing University of Information Science and Technology（南京信息工程大学）；University of Missouri-Kansas City（密苏里大学堪萨斯城分校）；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；Helmholtz Institute Freiberg for Resource Technology（亥姆霍兹弗赖贝格资源技术研究所）；University of Maryland, College Park（马里兰大学帕克分校）
Convolutional neural networks (CNNs) have been widely used for hyperspectral image classification. As a common process, small cubes are firstly cropped from the hyperspectral image and then fed into CNNs to extract spectral and spatial features. It is well known that different spectral bands and spatial positions in the cubes have different discriminative abilities. If fully explored, this prior information will help improve the learning capacity of CNNs. Along this direction, we propose an attention aided CNN model for spectral-spatial classification of hyperspectral images. Specifically, a s…
Recent years have witnessed great success for hand reconstruction in real-time applications such as visual reality and augmented reality while interacting with two-hand reconstruction through efficient transformers is left unexplored. In this paper, we propose a method called lightweight attention hand (LWA-HAND) to reconstruct hands in low flops from a single RGB image. To solve the occlusion and interaction problem in efficient attention architectures, we propose three mobile attention modules in this paper. The first module is a lightweight feature attention module that extracts both local …
Tampere University（坦佩雷大学）；Finnish Environment Institute（芬兰环境研究所）；Aarhus University（奥胡斯大学）
Recently, there has been an increasing interest in applying attention mechanisms in Convolutional Neural Networks (CNNs) to solve computer vision tasks. Most of these methods learn to explicitly identify and highlight relevant parts of the scene and pass the attended image to further layers of the network. In this paper, we argue that such an approach might not be optimal. Arguably, explicitly learning which parts of the image are relevant is typically harder than learning which parts of the image are less relevant and, thus, should be ignored. In fact, in vision domain, there are many easy-to…
The University of Edinburgh（爱丁堡大学）；Canon Medical Research Europe（佳能医疗研究欧洲公司）；The Alan Turing Institute（艾伦·图灵研究所）
We consider the problem of integrating non-imaging information into segmentation networks to improve performance. Conditioning layers such as FiLM provide the means to selectively amplify or suppress the contribution of different feature maps in a linear fashion. However, spatial dependency is difficult to learn within a convolutional paradigm. In this paper, we propose a mechanism to allow for spatial localisation conditioned on non-imaging information, using a feature-wise attention mechanism comprising a differentiable parametrised function (e.g. Gaussian), prior to applying the feature-wis…
Image restoration is an important and challenging task in computer vision. Reverting a filtered image to its original image is helpful in various computer vision tasks. We employ a nonlinear activation function free network (NAFNet) for a fast and lightweight model and add a color attention module that extracts useful color information for better accuracy. We propose an accurate, fast, lightweight network with multi-scale and color attention for Instagram filter removal (CAIR). Experiment results show that the proposed CAIR outperforms existing Instagram filter removal networks in fast and lig…
Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Emory University（埃默里大学）
We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs). Thereby our approach addresses the redundancy in CNNs that is also exposed by the recent success of lightweight CNNs. Lightweight CNNs can achieve comparable accuracy to standard CNNs with fewer parameters; however, the number of weights still scales quadratically with the CNN's width. Our MGIC architectures replace each CNN block with an MGIC counterpart that utilizes a hierarchy of nested grou…
Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between computational cost and detection accuracy, this paper presents a dual path network, named DPNet, for efficient object detection with lightweight self-attention. In backbone, a single input/output lightweight self-attention module (LSAM) is designed to encode global interactions between different positions. LSAM is also extended into a multiple-inputs version in feature pyramid network (FPN), which is employed to cap…
University of California, Berkeley（加州大学伯克利分校）；International Computer Science Institute（国际计算机科学研究所）
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filters over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimenta…
Hamburg University of Technology（汉堡工业大学）；University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）；DAISYlabs, Forschungszentrum Medizintechnik Hamburg（汉堡医疗技术研究中心DAISYlabs）
Objective: This work addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high class imbalance encountered in real-world multi-class datasets. Methods: To use high-resolution images, we propose a novel patch-based attention architecture that provides global context between small, high-resolution patches. We modify three pretrained architectures and study the performance of patch-based attention. To counter class imbalance problems, we …
The performance of convolutional neural networks (CNNs) can be improved by adjusting the interrelationship between channels with attention mechanism. However, attention mechanism in recent advance has not fully utilized spatial information of feature maps, which makes a great difference to the results of generated channel attentions. In this paper, we propose a novel network optimization module called Channel Reassessment Attention (CRA) module which uses channel attentions with spatial information of feature maps to enhance representational power of networks. We employ CRA module to assess ch…
Redundancy and noise exist in the bands of hyperspectral images (HSIs). Thus, it is a good property to be able to select suitable parts from hundreds of input bands for HSIs classification methods. In this letter, a band attention module (BAM) is proposed to implement the deep learning based HSIs classification with the capacity of band selection or weighting. The proposed BAM can be seen as a plug-and-play complementary component of the existing classification networks which fully considers the adverse effects caused by the redundancy of the bands when using convolutional neural networks (CNN…
In fine-grained image recognition (FGIR), the localization and amplification of region attention is an important factor, which has been explored a lot by convolutional neural networks (CNNs) based approaches. The recently developed vision transformer (ViT) has achieved promising results on computer vision tasks. Compared with CNNs, Image sequentialization is a brand new manner. However, ViT is limited in its receptive field size and thus lacks local attention like CNNs due to the fixed size of its patches, and is unable to generate multi-scale features to learn discriminative region attention.…
