Deep Convolutional Neural Networks (DCNN) have established a remarkable performance benchmark in the field of image classification, displacing classical approaches based on hand-tailored aggregations of local descriptors. Yet DCNNs impose high computational burdens both at training and at testing time, and training them requires collecting and annotating large amounts of training data. Supervised adaptation methods have been proposed in the literature that partially re-learn a transferred DCNN structure from a new target dataset. Yet these require expensive bounding-box annotations and are still computationally expensive to learn. In this paper, we address these shortcomings of DCNN adaptation schemes by proposing a hybrid approach that combines conventional, unsupervised aggregators such as Bag-of-Words (BoW), with the DCNN pipeline by treating the output of intermediate layers as densely extracted local descriptors.
We test a variant of our approach that uses only intermediate DCNN layers on the standard PASCAL VOC 2007 dataset and show performance significantly higher than the standard BoW model and comparable to Fisher vector aggregation but with a feature that is 150 times smaller. A second variant of our approach that includes the fully connected DCNN layers significantly outperforms Fisher vector schemes and performs comparably to DCNN approaches adapted to Pascal VOC 2007, yet at only a small fraction of the training and testing cost.
Huazhong University of Science and Technology（华中科技大学）
Script identification in the wild is of great importance in a multi-lingual robust-reading system. The scripts deriving from the same language family share a large set of characters, which makes script identification a fine-grained classification problem. Most existing methods make efforts to learn a single representation that combines the local features by making a weighted average or other clustering methods, which may reduce the discriminatory power of some important parts in each script for the interference of redundant features. In this paper, we present a novel module named Patch Aggrega…
Deriving an effective facial expression recognition component is important for a successful human-computer interaction system. Nonetheless, recognizing facial expression remains a challenging task. This paper describes a novel approach towards facial expression recognition task. The proposed method is motivated by the success of Convolutional Neural Networks (CNN) on the face recognition problem. Unlike other works, we focus on achieving good accuracy while requiring only a small sample data for training. Scale Invariant Feature Transform (SIFT) features are used to increase the performance on…
Jalpaiguri Government Engineering College（贾尔派古里政府工程学院）；Indian Institute of Information Technology, Sri City（斯里城印度信息技术学院）；Indian Statistical Institute（印度统计研究所）
Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional Neural Network (CNN) is one of the most frequently used deep learning based methods for visual data processing. The use of CNN for HSI classification is also visible in recent works. These approaches are mostly based on 2D CNN. Whereas, the HSI classification performance is highly dependent on both spatial and spectral information. Very few methods have utilized the 3D CNN because of increased computational complexity. This le…
School of Electrical Sciences, Indian Institute of Technology Bhubaneswar（印度理工学院布巴内斯瓦尔分校电气科学学院）
Classifying time series data using neural networks is a challenging problem when the length of the data varies. Video object trajectories, which are key to many of the visual surveillance applications, are often found to be of varying length. If such trajectories are used to understand the behavior (normal or anomalous) of moving objects, they need to be represented correctly. In this paper, we propose video object trajectory classification and anomaly detection using a hybrid Convolutional Neural Network (CNN) and Variational Autoencoder (VAE) architecture. First, we introduce a high level re…
Huaqiao University（华侨大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Person Re-IDentification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the element-wise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of w…
National University of Computer and Emerging Sciences（国立计算机与新兴科学大学）；University of Messina（墨西拿大学）；Bahauddin Zakariya University（巴哈丁·扎卡里亚大学）；Innopolis University（因诺波利斯大学）
Convolutional Neural Networks (CNN) has been extensively studied for Hyperspectral Image Classification (HSIC) more specifically, 2D and 3D CNN models have proved highly efficient in exploiting the spatial and spectral information of Hyperspectral Images. However, 2D CNN only considers the spatial information and ignores the spectral information whereas 3D CNN jointly exploits spatial-spectral information at a high computational cost. Therefore, this work proposed a lightweight CNN (3D followed by 2D-CNN) model which significantly reduces the computational cost by distributing spatial-spectral…
Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for the ordinary convolutional neural network (CNN) to train in general scenes to catch subtle lane feature from the raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of …
Convolutional Neural Networks (CNNs) have demonstrated their superiority in image classification, and evolutionary computation (EC) methods have recently been surging to automatically design the architectures of CNNs to save the tedious work of manually designing CNNs. In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN. There are three new ideas in the proposed DECNN method. Firstly, an existing effective encoding scheme is refined to cater for variable-leng…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；T. J. Watson Research Center, IBM（IBM T.J.沃森研究中心）；Inspirit IoT, Inc（英思普瑞特物联网公司）
Deep Convolutional Neural Networks have become a Swiss knife in solving critical artificial intelligence tasks. However, deploying deep CNN models for latency-critical tasks remains to be challenging because of the complex nature of CNNs. Recently, FPGA has become a favorable device to accelerate deep CNNs thanks to its high parallel processing capability and energy efficiency. In this work, we explore different fast convolution algorithms including Winograd and Fast Fourier Transform (FFT), and find an optimal strategy to apply them together on different types of convolutions. We also propose…
The University of Sydney（悉尼大学）；Stevens Institute of Technology（斯蒂文斯理工学院）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）；JD Explore Academy（京东探索学院）
In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs). We begin by developing a vanilla 1-bit GNN framework that binarizes both the GNN parameters and the graph features. Despite the lightweight architecture, we observed that this vanilla framework suffered from insufficient discriminative power in distinguishing graph topologies, leading to a dramatic drop in performance. This discovery motivates us to devise meta aggregators to improve the expressive power of vanilla binarized GNNs, of which the aggregation schemes can be adaptively changed i…
CAMS: Convolution and Attention-Free Mamba-based Cardiac Image Segmentation
School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦玛丽女王大学电子工程与计算机科学学院）；Queen Mary’s Digital Environment Research Institute (DERI)（伦敦玛丽女王大学数字环境研究所）；Department of Computer Science, University College London（伦敦大学学院计算机科学系）；School of Engineering and Materials Science, Queen Mary University of London（伦敦玛丽女王大学工程与材料科学学院）
University of Electronic Science and Technology of China（电子科技大学）
This paper describes our submission to the fourth Affective Behavior Analysis (ABAW) competition. We proposed a hybrid CNN-Transformer model for the Multi-Task-Learning (MTL) and Learning from Synthetic Data (LSD) task. Experimental results on validation dataset shows that our method achieves better performance than baseline model, which verifies that the effectiveness of proposed network.
Machine learning methods are used today for most recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal albums or other similar environs where the size of training dataset is a limitation, within the framework of a proposed hybrid CNN-AIS model. We use Artificial Immune System Principles to enhance small size of training data set. A layer of Clonal Selection is added to the local filtering and max pooling …
Graz University of Technology（格拉茨技术大学）；AIT Austrian Institute of Technology（奥地利技术研究所）
We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply a recently proposed highly parallel dual block descent algorithm which only needs a small fixed number of iterations to compute a high-quality approximate minimizer. As the main contribution of th…
National Taiwan University of Science and Technology（国立台湾科技大学）
Pruning redundant filters in CNN models has received growing attention. In this paper, we propose an adaptive binary search-first hybrid pyramid- and clustering-based (ABSHPC-based) method for pruning filters automatically. In our method, for each convolutional layer, initially a hybrid pyramid data structure is constructed to store the hierarchical information of each filter. Given a tolerant accuracy loss, without parameters setting, we begin from the last convolutional layer to the first layer; for each considered layer with less or equal pruning rate relative to its previous layer, our ABS…
Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation
Graduate School of Data Science, Chonnam National University（全南国立大学数据科学研究生院）；Department of Computer Science, National Yang Ming Chiao Tung University（国立阳明交通大学计算机科学系）；Digital Transformation Center, FPT Telecom（FPT电信数字化转型中心）；AI Graduate School, GIST（光州科学技术院人工智能研究生院）
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…
Diabetic retinopathy (DR) is a leading cause of vision loss among middle-aged and elderly people, which significantly impacts their daily lives and mental health. To improve the efficiency of clinical screening and enable the early detection of DR, a variety of automated DR diagnosis systems have been recently established based on convolutional neural network (CNN) or vision Transformer (ViT). However, due to the own shortages of CNN / ViT, the performance of existing methods using single-type backbone has reached a bottleneck. One potential way for the further improvements is integrating diff…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；National University of Singapore（新加坡国立大学）
Convolutional neural network (CNN) has achieved state-of-the-art performance in many different visual tasks. Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features. Moreover, CNN features are also transferable among different domains. On the other hand, traditional dictionarybased features (such as BoW and SPM) contain much more local discriminative and structural information, which is implicitly embedded in the images. To further improve the performance, in this paper, we propose to combine CNN with dictionarybased mo…
University of Wisconsin-Eau Claire（威斯康星大学欧克莱尔分校）；Minnesota State University, Mankato（明尼苏达州立大学曼卡托分校）
Social media is currently being used by many individuals online as a major source of information. However, not all information shared online is true, even photos and videos can be doctored. Deepfakes have recently risen with the rise of technological advancement and have allowed nefarious online users to replace one face with a computer generated face of anyone they would like, including important political and cultural figures. Deepfakes are now a tool to be able to spread mass misinformation. There is now an immense need to create models that are able to detect deepfakes and keep them from b…
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Calgary（卡尔加里大学）
The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse multimodal images. In the encoder, a non-local cross-modal attention block is proposed to capture both local and global dependencies of multiple source images. A branch fusion module is designed to adaptively fuse the features of the two branches. We embed a Transformer module with linear complexity in the decoder to enhance the reconstruction capability of…
LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification
Ramakrishna Mission Vidyamandira（拉马克里希纳使命学院）；Indian Institute of Information Technology (IIIT)（印度信息与技术学院）；Norwegian University of Science and Technology (NTNU)（挪威科学与技术大学）
Hybrid CNN-BYOL Approach for Fault Detection in Induction Motors Using Thermal Images
Department of Computer Science and Engineering（计算机科学与工程系）；Bangladesh Army University of Science and Technology (BAUST)（孟加拉国陆军科学与技术大学）；School of Computer Science and Engineering（计算机科学与工程学院）；The University of Aizu（立命馆大学）
Hybrid images is a technique to generate images with two interpretations that change as a function of viewing distance. It has been utilized to study multiscale processing of images by the human visual system. Using 63,000 hybrid images across 10 fruit categories, here we show that predictions of deep learning vision models qualitatively matches with the human perception of these images. Our results provide yet another evidence in support of the hypothesis that Convolutional Neural Networks (CNNs) and Transformers are good at modeling the feedforward sweep of information in the ventral stream …
CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer Detection
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada（计算机科学与软件工程系，康科迪亚大学，加拿大蒙特利尔）；Ebovir Biotechnologie Inc., Montreal, Canada（Ebovir生物技术公司，加拿大蒙特利尔）
Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution operations. Transformer based methods are capable of modelling long-range dependencies of information for capturing global representations, yet their ability to model local context is lacking. Integrating CNN and Transformer to learn both local and global representations while exploring multi-scale features is instrumental in further improving medical image…
Xinjiang University（新疆大学）；Shandong University of Technology（山东理工大学）
Although Convolutional Neural Networks (CNN) have made good progress in image restoration, the intrinsic equivalence and locality of convolutions still constrain further improvements in image quality. Recent vision transformer and self-attention have achieved promising results on various computer vision tasks. However, directly utilizing Transformer for image restoration is a challenging task. In this paper, we introduce an effective hybrid architecture for sand image restoration tasks, which leverages local features from CNN and long-range dependencies captured by transformer to improve the r…
We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images. The model is unique in forming a nonlinear combination of three traditional interpolation techniques using the convolutional neural network. Another proposed architecture uses a skip connection with nearest neighbor interpolation, achieving almost similar results. The architectures have been carefully designed to ensure that the reconstructed images lie precisely in the manifold of high-resolution images, thereby preserving the high-frequency components with…
University of Electronic Science and Technology of China（电子科技大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Pedestrian detection has achieved great improvements with the help of Convolutional Neural Networks (CNNs). CNN can learn high-level features from input images, but the insufficient spatial resolution of CNN feature channels (feature maps) may cause a loss of information, which is harmful especially to small instances. In this paper, we propose a new pedestrian detection framework, which extends the successful RPN+BF framework to combine handcrafted features and CNN features. RoI-pooling is used to extract features from both handcrafted channels (e.g. HOG+LUV, CheckerBoards or RotatedFilters) …
MSLAU-Net: A Hybrid CNN-Transformer Network for Medical Image Segmentation
College of Computer Science and Engineering（计算机科学与工程学院）；College of Artificial Intelligence（人工智能学院）；Department of Pharmacy（药学部）；Department of Prosthodontics（修复学部）；Chongqing Key Laboratory of Oral Diseases（重庆口腔疾病重点实验室）；Chongqing Municipal Key Laboratory of Oral Biomedical Engineering of Higher Education（重庆市口腔生物医学工程高等教育重点实验室）；School of Computer Science and Engineering（计算机科学与工程学院）；Southeast University（东南大学）
Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, India（计算机科学与工程系，印度理工学院Kharagpur分校）；Department of Electrical and Electronic Engineering, Chittagong University of Engineering and Technology, Bangladesh（电气与电子工程系，查塔格工学院）
Deep learning approaches have reached a celebrity status in artificial intelligence field, its success have mostly relied on Convolutional Networks (CNN) and Recurrent Networks. By exploiting fundamental spatial properties of images and videos, the CNN always achieves dominant performance on visual tasks. And the Recurrent Networks (RNN) especially long short-term memory methods (LSTM) can successfully characterize the temporal correlation, thus exhibits superior capability for time series tasks. Traffic flow data have plentiful characteristics on both time and space domain. However, applicati…
School of Information and Communication Technology（信息与通信技术学院）；University of Tasmania（塔斯马尼亚大学）
Convolutional neural network (CNN) models have seen advanced improvements in performance in various domains, but lack of interpretability is a major barrier to assurance and regulation during operation for acceptance and deployment of AI-assisted applications. There have been many works on input interpretability focusing on analyzing the input-output relations, but the internal logic of models has not been clarified in the current mainstream interpretability methods. In this study, we propose a novel hybrid CNN-interpreter through: (1) An original forward propagation mechanism to examine the l…
Tiangong University（天津工业大学）；University of Wollongong（伍伦贡大学）
Recently, deep learning has attracted more and more attention in phase unwrapping of fringe projection three-dimensional (3D) measurement, with the aim to improve the performance leveraging the powerful Convolutional Neural Network (CNN) models. In this paper, for the first time (to the best of our knowledge), we introduce the Transformer into the phase unwrapping which is different from CNN and propose Hformer model dedicated to phase unwrapping via fringe order prediction. The proposed model has a hybrid CNN-Transformer architecture that is mainly composed of backbone, encoder and decoder to…
