Rui-Yang Ju

Rui-Yang Ju, Ting-Yu Lin, Jia-Hao Jian et al.

With the good performance of deep learning algorithms in the field of computer vision (CV), the convolutional neural network (CNN) architecture has become a main backbone of the computer vision task. With the widespread use of mobile devices, neural network models based on platforms with low computing power are gradually being paid attention. However, due to the limitation of computing power, deep learning algorithms are usually not available on mobile devices. This paper proposes a lightweight convolutional neural network, TripleNet, which can operate easily on Raspberry Pi. Adopted from the concept of block connections in ThreshNet, the newly proposed network model compresses and accelerates the network model, reduces the amount of parameters of the network, and shortens the inference time of each image while ensuring the accuracy. Our proposed TripleNet and other state-of-the-art (SOTA) neural networks perform image classification experiments with the CIFAR-10 and SVHN datasets on Raspberry Pi. The experimental results show that, compared with GhostNet, MobileNet, ThreshNet, EfficientNet, and HarDNet, the inference time of TripleNet per image is shortened by 15%, 16%, 17%, 24%, and 30%, respectively. The detail codes of this work are available at https://github.com/RuiyangJu/TripleNet.

Rui-Yang Ju, Chih-Chia Chen, Jen-Shiun Chiang et al.

The Transformer-based method has demonstrated remarkable performance for image super-resolution in comparison to the method based on the convolutional neural networks (CNNs). However, using the self-attention mechanism like SwinIR (Image Restoration Using Swin Transformer) to extract feature information from images needs a significant amount of computational resources, which limits its application on low computing power platforms. To improve the model feature reuse, this research work proposes the Interval Dense Connection Strategy, which connects different blocks according to the newly designed algorithm. We apply this strategy to SwinIR and present a new model, which named SwinOIR (Object Image Restoration Using Swin Transformer). For image super-resolution, an ablation study is conducted to demonstrate the positive effect of the Interval Dense Connection Strategy on the model performance. Furthermore, we evaluate our model on various popular benchmark datasets, and compare it with other state-of-the-art (SOTA) lightweight models. For example, SwinOIR obtains a PSNR of 26.62 dB for x4 upscaling image super-resolution on Urban100 dataset, which is 0.15 dB higher than the SOTA model SwinIR. For real-life application, this work applies the lastest version of You Only Look Once (YOLOv8) model and the proposed model to perform object detection and real-life image super-resolution on low-quality images. This implementation code is publicly available at https://github.com/Rubbbbbbbbby/SwinOIR.

Rui-Yang Ju, Yu-Shian Lin, Yanlin Jin et al.

The efficient extraction of text information from the background in degraded color document images is an important challenge in the preservation of ancient manuscripts. The imperfect preservation of ancient manuscripts has led to different types of degradation over time, such as page yellowing, staining, and ink bleeding, seriously affecting the results of document image binarization. This work proposes an effective three-stage network method to image enhancement and binarization of degraded documents using generative adversarial networks (GANs). Specifically, in Stage-1, we first split the input images into multiple patches, and then split these patches into four single-channel patch images (gray, red, green, and blue). Then, three single-channel patch images (red, green, and blue) are processed by the discrete wavelet transform (DWT) with normalization. In Stage-2, we use four independent generators to separately train GAN models based on the four channels on the processed patch images to extract color foreground information. Finally, in Stage-3, we train two independent GAN models on the outputs of Stage-2 and the resized original input images (512x512) as the local and global predictions to obtain the final outputs. The experimental results show that the Avg-Score metrics of the proposed method are 77.64, 77.95, 79.05, 76.38, 75.34, and 77.00 on the (H)-DIBCO 2011, 2013, 2014, 2016, 2017, and 2018 datasets, which are at the state-of-the-art level. The implementation code for this work is available at https://github.com/abcpp12383/ThreeStageBinarization.

Rui-Yang Ju, Chun-Tse Chien, Jen-Shiun Chiang

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first, and prepare for the surgery based on the analysis of the X-ray images. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection for Computer-Assisted Diagnosis, where the YOLOv8 model has obtained the satisfactory results. Applying the attention modules to neural networks is one of the effective methods to improve the model performance. This paper proposes YOLOv8-ResCBAM, which incorporates Convolutional Block Attention Module integrated with resblock (ResCBAM) into the original YOLOv8 network architecture. The experimental results on the GRAZPEDWRI-DX dataset demonstrate that the mean Average Precision calculated at Intersection over Union threshold of 0.5 (mAP 50) of the proposed model increased from 63.6% of the original YOLOv8 model to 65.8%, which achieves the state-of-the-art performance. The implementation code is available at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.

Rui-Yang Ju, Chun-Tse Chien, Chia-Min Lin et al.

Children often suffer wrist injuries in daily life, while fracture injuring radiologists usually need to analyze and interpret X-ray images before surgical treatment by surgeons. The development of deep learning has enabled neural network models to work as computer-assisted diagnosis (CAD) tools to help doctors and experts in diagnosis. Since the YOLOv8 models have obtained the satisfactory success in object detection tasks, it has been applied to fracture detection. The Global Context (GC) block effectively models the global context in a lightweight way, and incorporating it into YOLOv8 can greatly improve the model performance. This paper proposes the YOLOv8+GC model for fracture detection, which is an improved version of the YOLOv8 model with the GC block. Experimental results demonstrate that compared to the original YOLOv8 model, the proposed YOLOv8-GC model increases the mean average precision calculated at intersection over union threshold of 0.5 (mAP 50) from 63.58% to 66.32% on the GRAZPEDWRI-DX dataset, achieving the state-of-the-art (SOTA) level. The implementation code for this work is available on GitHub at https://github.com/RuiyangJu/YOLOv8_Global_Context_Fracture_Detection.

Rui-Yang Ju, KokSheik Wong, Jen-Shiun Chiang

The outcome of text recognition for degraded color documents is often unsatisfactory due to interference from various contaminants. To extract information more efficiently for text recognition, document image enhancement and binarization are often employed as preliminary steps in document analysis. Training independent generative adversarial networks (GANs) for each color channel can generate images where shadows and noise are effectively removed, which subsequently allows for efficient text information extraction. However, employing multiple GANs for different color channels requires long training and inference times. To reduce both the training and inference times of these preliminary steps, we propose an efficient method based on multi-scale feature extraction, which incorporates Haar wavelet transformation and normalization to process document images before submitting them to GANs for training. Experiment results show that our proposed method significantly reduces both the training and inference times while maintaining comparable performances when benchmarked against the state-of-the-art methods. In the best case scenario, a reduction of 10% and 26% are observed for training and inference times, respectively, while maintaining the model performance at 73.79 of Average-Score metric. The implementation of this work is available at https://github.com/RuiyangJu/Efficient_Document_Image_Binarization.

Rui-Yang Ju, Jen-Shiun Chiang, Chih-Chia Chen et al.

Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network train better, and skip connection (residual learning) can improve network model performance. For the image classification task, models with global densely connected architectures perform well in large datasets like ImageNet, but are not suitable for small datasets such as CIFAR-10 and SVHN. Different from dense connections, we propose two new algorithms to connect layers. Baseline is a densely connected network, and the networks connected by the two new algorithms are named ShortNet1 and ShortNet2 respectively. The experimental results of image classification on CIFAR-10 and SVHN show that ShortNet1 has a 5% lower test error rate and 25% faster inference time than Baseline. ShortNet2 speeds up inference time by 40% with less loss in test accuracy. Code and pre-trained models are available at https://github.com/RuiyangJu/Connection_Reduction.

Yanlin Jin, Rui-Yang Ju, Haojun Liu et al.

Deep visual odometry, despite extensive research, still faces limitations in accuracy and generalizability that prevent its broader application. To address these challenges, we propose an Oriented FAST and Rotated BRIEF (ORB)-guided visual odometry with selective online adaptation named ORB-SfMLearner. We present a novel use of ORB features for learning-based ego-motion estimation, leading to more robust and accurate results. We also introduce the cross-attention mechanism to enhance the explainability of PoseNet and have revealed that driving direction of the vehicle can be explained through the attention weights. To improve generalizability, our selective online adaptation allows the network to rapidly and selectively adjust to the optimal parameters across different domains. Experimental results on KITTI and vKITTI datasets show that our method outperforms previous state-of-the-art deep visual odometry methods in terms of ego-motion accuracy and generalizability. Code is available at https://github.com/PeaceNeil/ORB-SfMLearner

Rui-Yang Ju, Jen-Shiun Chiang

Virtual try-on systems allow users to interactively try different products within VR scenarios. However, most existing VTON methods operate only on predefined eyewear templates and lack support for fine-grained, user-driven customization. While GlassesGAN enables personalized 2D eyewear design, its capability remains limited to 2D image generation. Motivated by the success of 3D Gaussian Blendshapes in head reconstruction, we integrate these two techniques and propose GlassesGB, a framework that supports customizable eyewear generation for 3D head avatars. GlassesGB effectively bridges 2D generative customization with 3D head avatar rendering, addressing the challenge in achieving personalized eyewear design for VR applications. The implementation code is available at https://ruiyangju.github.io/GlassesGB.

Rui-Yang Ju, Weiming Cai

Hospital emergency departments frequently receive lots of bone fracture cases, with pediatric wrist trauma fracture accounting for the majority of them. Before pediatric surgeons perform surgery, they need to ask patients how the fracture occurred and analyze the fracture situation by interpreting X-ray images. The interpretation of X-ray images often requires a combination of techniques from radiologists and surgeons, which requires time-consuming specialized training. With the rise of deep learning in the field of computer vision, network models applying for fracture detection has become an important research topic. In this paper, we use data augmentation to improve the model performance of YOLOv8 algorithm (the latest version of You Only Look Once) on a pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX), which is a public dataset. The experimental results show that our model has reached the state-of-the-art (SOTA) mean average precision (mAP 50). Specifically, mAP 50 of our model is 0.638, which is significantly higher than the 0.634 and 0.636 of the improved YOLOv7 and original YOLOv8 models. To enable surgeons to use our model for fracture detection on pediatric wrist trauma X-ray images, we have designed the application "Fracture Detection Using YOLOv8 App" to assist surgeons in diagnosing fractures, reducing the probability of error analysis, and providing more useful information for surgery.

Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou et al.

The introduction of YOLOv9, the latest version of the You Only Look Once (YOLO) series, has led to its widespread adoption across various scenarios. This paper is the first to apply the YOLOv9 algorithm model to the fracture detection task as computer-assisted diagnosis (CAD) to help radiologists and surgeons to interpret X-ray images. Specifically, this paper trained the model on the GRAZPEDWRI-DX dataset and extended the training set using data augmentation techniques to improve the model performance. Experimental results demonstrate that compared to the mAP 50-95 of the current state-of-the-art (SOTA) model, the YOLOv9 model increased the value from 42.16% to 43.73%, with an improvement of 3.7%. The implementation code is publicly available at https://github.com/RuiyangJu/YOLOv9-Fracture-Detection.

Rui-Yang Ju, Ting-Yu Lin, Jen-Shiun Chiang et al.

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image classification, object detection, semantic segmentation, etc.), state-of-the-art convolutional neural networks have introduced some concepts of Transformer. This proves that Transformer has a good prospect in the field of image recognition. After Vision Transformer was proposed, more and more works began to use self-attention to completely replace the convolutional layer. This work is based on Vision Transformer, combined with the pyramid architecture, using Split-transform-merge to propose the group encoder and name the network architecture Aggregated Pyramid Vision Transformer (APVT). We perform image classification tasks on the CIFAR-10 dataset and object detection tasks on the COCO 2017 dataset. Compared with other network architectures that use Transformer as the backbone, APVT has excellent results while reducing the computational cost. We hope this improved strategy can provide a reference for future Transformer research in computer vision.

Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou et al.

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first and prepare for it based on the analysis of the radiologist. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection as computer-assisted diagnosis (CAD). In 2023, Ultralytics presented the latest version of the YOLO models, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the hottest methods to improve the model performance. This research work proposes YOLOv8-AM, which incorporates the attention mechanism into the original YOLOv8 architecture. Specifically, we respectively employ four attention modules, Convolutional Block Attention Module (CBAM), Global Attention Mechanism (GAM), Efficient Channel Attention (ECA), and Shuffle Attention (SA), to design the improved models and train them on GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP 50) of the YOLOv8-AM model based on ResBlock + CBAM (ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. Conversely, YOLOv8-AM model incorporating GAM obtains the mAP 50 value of 64.2%, which is not a satisfactory enhancement. Therefore, we combine ResBlock and GAM, introducing ResGAM to design another new YOLOv8-AM model, whose mAP 50 value is increased to 65.0%. The implementation code for this study is available on GitHub at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.

Rui-Yang Ju, KokSheik Wong, Yanlin Jin et al.

Document image enhancement and binarization are commonly performed prior to document analysis and recognition tasks for improving the efficiency and accuracy of optical character recognition (OCR) systems. This is because directly recognizing text in degraded documents, particularly in color images, often results in unsatisfactory recognition performance. To address these issues, existing methods train independent generative adversarial networks (GANs) for different color channels to remove shadows and noise, which, in turn, facilitates efficient text information extraction. However, deploying multiple GANs results in long training and inference times. To reduce both training and inference times of document image enhancement and binarization models, we propose MFE-GAN, an efficient GAN-based framework with multi-scale feature extraction (MFE), which incorporates Haar wavelet transformation (HWT) and normalization to process document images before feeding them into GANs for training. In addition, we present novel generators, discriminators, and loss functions to improve the model's performance, and we conduct ablation studies to demonstrate their effectiveness. Experimental results on the Benchmark, Nabuco, and CMATERdb datasets demonstrate that the proposed MFE-GAN significantly reduces the total training and inference times while maintaining comparable performance with respect to state-of-the-art (SOTA) methods. The implementation of this work is available at https://ruiyangju.github.io/MFE-GAN.

Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko et al.

Kuzushiji was one of the most popular writing styles in pre-modern Japan and was widely used in both personal letters and official documents. However, due to its highly cursive forms and extensive glyph variations, most modern Japanese readers cannot directly interpret Kuzushiji characters. Therefore, recent research has focused on developing automated Kuzushiji character recognition methods, which have achieved satisfactory performance on relatively clean Kuzushiji document images. However, existing methods struggle to maintain recognition accuracy under seal interference (e.g., when seals overlap characters), despite the frequent occurrence of seals in pre-modern Japanese documents. To address this challenge, we propose a three-stage restoration-guided Kuzushiji character recognition (RG-KCR) framework specifically designed to mitigate seal interference. We construct datasets for evaluating Kuzushiji character detection (Stage 1) and classification (Stage 3). Experimental results show that the YOLOv12-medium model achieves a precision of 98.0% and a recall of 93.3% on the constructed test set. We quantitatively evaluate the restoration performance of Stage 2 using PSNR and SSIM. In addition, we conduct an ablation study to demonstrate that Stage 2 improves the Top-1 accuracy of Metom, a Vision Transformer (ViT)-based Kuzushiji classifier employed in Stage 3, from 93.45% to 95.33%. The implementation code of this work is available at https://ruiyangju.github.io/RG-KCR.

Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko et al.

Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan. With the rapid development of deep learning, researchers have begun applying Optical Character Recognition (OCR) techniques to transcribe Kuzushiji into modern Japanese. Although existing OCR methods perform well on clean pre-modern Japanese documents written in Kuzushiji, they often fail to consider various types of noise, such as document degradation and seals, which significantly affect recognition accuracy. To the best of our knowledge, no existing dataset specifically addresses these challenges. To address this gap, we introduce the Degraded Kuzushiji Documents with Seals (DKDS) dataset as a new benchmark for related tasks. We describe the dataset construction process, which required the assistance of a trained Kuzushiji expert, and define two benchmark tracks: (1) text and seal detection and (2) document binarization. For the text and seal detection track, we provide baseline results using multiple versions of the You Only Look Once (YOLO) models for detecting Kuzushiji characters and seals. For the document binarization track, we present baseline results from traditional binarization algorithms, traditional algorithms combined with K-means clustering, and Generative Adversarial Network (GAN)-based methods. The DKDS dataset and the implementation code for baseline methods are available at https://ruiyangju.github.io/DKDS.

Rui-Yang Ju, Sheng-Yen Huang, Yi-Ping Hung

The introduction of 3D Gaussian blendshapes has enabled the real-time reconstruction of animatable head avatars from monocular video. Toonify, a StyleGAN-based method, has become widely used for facial image stylization. To extend Toonify for synthesizing diverse stylized 3D head avatars using Gaussian blendshapes, we propose an efficient two-stage framework, ToonifyGB. In Stage 1 (stylized video generation), we adopt an improved StyleGAN to generate the stylized video from the input video frames, which overcomes the limitation of cropping aligned faces at a fixed resolution as preprocessing for normal StyleGAN. This process provides a more stable stylized video, which enables Gaussian blendshapes to better capture the high-frequency details of the video frames, facilitating the synthesis of high-quality animations in the next stage. In Stage 2 (Gaussian blendshapes synthesis), our method learns a stylized neutral head model and a set of expression blendshapes from the generated stylized video. By combining the neutral head model with expression blendshapes, ToonifyGB can efficiently render stylized avatars with arbitrary expressions. We validate the effectiveness of ToonifyGB on benchmark datasets using two representative styles: Arcane and Pixar.

Yanbing Bai, Zihao Yang, Jinze Yu et al.

With the escalating frequency of floods posing persistent threats to human life and property, satellite remote sensing has emerged as an indispensable tool for monitoring flood hazards. SpaceNet8 offers a unique opportunity to leverage cutting-edge artificial intelligence technologies to assess these hazards. A significant contribution of this research is its application of Apache Sedona, an advanced platform specifically designed for the efficient and distributed processing of large-scale geospatial data. This platform aims to enhance the efficiency of error analysis, a critical aspect of improving flood damage detection accuracy. Based on Apache Sedona, we introduce a novel approach that addresses the challenges associated with inaccuracies in flood damage detection. This approach involves the retrieval of cases from historical flood events, the adaptation of these cases to current scenarios, and the revision of the model based on clustering algorithms to refine its performance. Through the replication of both the SpaceNet8 baseline and its top-performing models, we embark on a comprehensive error analysis. This analysis reveals several main sources of inaccuracies. To address these issues, we employ data visual interpretation and histogram equalization techniques, resulting in significant improvements in model metrics. After these enhancements, our indicators show a notable improvement, with precision up by 5%, F1 score by 2.6%, and IoU by 4.5%. This work highlights the importance of advanced geospatial data processing tools, such as Apache Sedona. By improving the accuracy and efficiency of flood detection, this research contributes to safeguarding public safety and strengthening infrastructure resilience in flood-prone areas, making it a valuable addition to the field of remote sensing and disaster management.

Yanbing Bai, Rui-Yang Ju, Lemeng Zhao et al.

Unmanned Aerial Vehicles (UAVs) have become increasingly important in disaster emergency response by enabling real-time aerial video analysis. Due to the limited computational resources available on UAVs, large models cannot be run independently for real-time analysis. To overcome this challenge, we propose a lightweight and efficient two-stage framework for real-time wildfire monitoring and fire source detection on UAV platforms. Specifically, in Stage 1, we utilize a policy network to identify and discard redundant video clips using frame compression techniques, thereby reducing computational costs. In addition, we introduce a station point mechanism that leverages future frame information within the sequential policy network to improve prediction accuracy. In Stage 2, once the frame is classified as "fire", we employ the improved YOLOv8 model to localize the fire source. We evaluate the Stage 1 method using the FLAME and HMDB51 datasets, and the Stage 2 method using the Fire & Smoke dataset. Experimental results show that our method significantly reduces computational costs while maintaining classification accuracy in Stage 1, and achieves higher detection accuracy with similar inference time in Stage 2 compared to baseline methods.

Yanbing Bai, Siao Li, Rui-Yang Ju et al.

Illegal, unreported, and unregulated (IUU) fishing activities seriously affect various aspects of human life. However, traditional methods for detecting and monitoring IUU fishing activities at sea have limitations. Although synthetic aperture radar (SAR) can complement existing vessel detection systems, extracting useful information from SAR images using traditional methods remains a challenge, especially in IUU fishing. This paper proposes a deep learning based fishing activity detection system, which is implemented on the xView3 dataset using six classical object detection models: SSD, RetinaNet, FSAF, FCOS, Faster R-CNN, and Cascade R-CNN. In addition, this work employs different enhancement techniques to improve the performance of the Faster R-CNN model. The experimental results demonstrate that training the Faster R-CNN model using the Online Hard Example Mining (OHEM) strategy increases the Avg-F1 value from 0.212 to 0.216.

Rui-Yang Ju, Yu-Shian Lin, Jen-Shiun Chiang et al.

To efficiently extract textual information from color degraded document images is a significant research area. The prolonged imperfect preservation of ancient documents has led to various types of degradation, such as page staining, paper yellowing, and ink bleeding. These types of degradation badly impact the image processing for features extraction. This paper introduces a novelty method employing generative adversarial networks based on color channel using discrete wavelet transform (CCDWT-GAN). The proposed method involves three stages: image preprocessing, image enhancement, and image binarization. In the initial step, we apply discrete wavelet transform (DWT) to retain the low-low (LL) subband image, thereby enhancing image quality. Subsequently, we divide the original input image into four single-channel colors (red, green, blue, and gray) to separately train adversarial networks. For the extraction of global and local features, we utilize the output image from the image enhancement stage and the entire input image to train adversarial networks independently, and then combine these two results as the final output. To validate the positive impact of the image enhancement and binarization stages on model performance, we conduct an ablation study. This work compares the performance of the proposed method with other state-of-the-art (SOTA) methods on DIBCO and H-DIBCO ((Handwritten) Document Image Binarization Competition) datasets. The experimental results demonstrate that CCDWT-GAN achieves a top two performance on multiple benchmark datasets. Notably, on DIBCO 2013 and 2016 dataset, our method achieves F-measure (FM) values of 95.24 and 91.46, respectively.

Rui-Yang Ju, Ting-Yu Lin, Jia-Hao Jian et al.

With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature maps to solve the model depth problem. Although this network architecture has excellent accuracy with low parameters, it requires an excessive inference time. To solve this problem, HarDNet reduces the connections between the feature maps, making the remaining connections resemble harmonic waves. However, this compression method may result in a decrease in the model accuracy and an increase in the parameters and model size. This network architecture may reduce the memory access time, but its overall performance can still be improved. Therefore, we propose a new network architecture, ThreshNet, using a threshold mechanism to further optimize the connection method. Different numbers of connections for different convolution layers are discarded to accelerate the inference of the network. The proposed network has been evaluated with image classification using CIFAR 10 and SVHN datasets under platforms of NVIDIA RTX 3050 and Raspberry Pi 4. The experimental results show that, compared with HarDNet68, GhostNet, MobileNetV2, ShuffleNet, and EfficientNet, the inference time of the proposed ThreshNet79 is 5%, 9%, 10%, 18%, and 20% faster, respectively. The number of parameters of ThreshNet95 is 55% less than that of HarDNet85. The new model compression and model acceleration methods can speed up the inference time, enabling network models to operate on mobile devices.

Rui-Yang Ju, Ting-Yu Lin, Jen-Shiun Chiang

Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the most advanced neural network architectures, DenseNet, has achieved excellent convergence rates through dense connections. However, it still has obvious shortcomings in the usage of amount of memory. In this paper, we introduce a new type of pruning tool, threshold, which refers to the principle of the threshold voltage in MOSFET. This work employs this method to connect blocks of different depths in different ways to reduce the usage of memory. It is denoted as ThresholdNet. We evaluate ThresholdNet and other different networks on datasets of CIFAR10. Experiments show that HarDNet is twice as fast as DenseNet, and on this basis, ThresholdNet is 10% faster and 10% lower error rate than HarDNet.