Multi-granularity pruning for deep residual networks

2020 ◽  
Vol 39 (5) ◽  
pp. 7403-7410
Author(s):  
Yangke Huang ◽  
Zhiming Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Compression Ratio ◽  
Gradient Descent ◽  
Computational Cost ◽  
Deep Convolutional Neural Networks ◽  
Acceleration Ratio ◽  
Network Pruning ◽  
High Computational Cost ◽  
Pruning Methods

Network pruning has been widely used to reduce the high computational cost of deep convolutional neural networks(CNNs). The dominant pruning methods, channel pruning, removes filters in layers based on their importance or sparsity training. But these methods often give limited acceleration ratio and encounter difficulties when pruning CNNs with skip connections. Block pruning methods take a sequence of consecutive layers (e.g., Conv-BN-ReLu) as a block and remove entire block each time. However, previous methods usually introduce new parameters to help pruning and lead additional parameters and extra computations. This work proposes a novel multi-granularity pruning approach that combines block pruning with channel pruning (BPCP). The block pruning (BP) module remove blocks by directly searches the redundant blocks with gradient descent and leaves no extra parameters in final models, which is friendly to hardware optimization. The channel pruning (CP) module remove redundant channels based on importance criteria and handles CNNs with skip connections properly, which further improves the overall compression ratio. As a result, for CIFAR10, BPCP reduces the number of parameters and MACs of a ResNet56 model up to 78.9% and 80.3% respectively with <3% accuracy drop. In terms of speed, it gives a 3.17 acceleration ratio. Our code has been made available at https://github.com/Pokemon-Huang/BPCP.

scholarly journals Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

2021 ◽  
Author(s):  
Mohammed Abdulla Salim Al Husaini ◽  
Mohamed Hadi Habaebi ◽  
Teddy Surya Gunawan ◽  
Md Rafiqul Islam ◽  
Elfatih A. A. Elsheikh ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Early Stage ◽  
Computational Cost ◽  
Optimization Methods ◽  
Optimization Method ◽  
Deep Convolutional Neural Networks ◽  
Breast Thermography

AbstractBreast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3–30 were used in conjunction with learning rates 1 × 10–3, 1 × 10–4 and 1 × 10–5, Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 × 10–4, and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20–30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.

Hybrid pooling with wavelets for convolutional neural networks

2022 ◽  
pp. 1-10
Author(s):  
Daniel Trevino-Sanchez ◽  
Vicente Alarcon-Aquino
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Computational Cost ◽  
Relevant Information ◽  
Accuracy Improvement ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Augmentation Techniques ◽  
High Computational Cost

The need to detect and classify objects correctly is a constant challenge, being able to recognize them at different scales and scenarios, sometimes cropped or badly lit is not an easy task. Convolutional neural networks (CNN) have become a widely applied technique since they are completely trainable and suitable to extract features. However, the growing number of convolutional neural networks applications constantly pushes their accuracy improvement. Initially, those improvements involved the use of large datasets, augmentation techniques, and complex algorithms. These methods may have a high computational cost. Nevertheless, feature extraction is known to be the heart of the problem. As a result, other approaches combine different technologies to extract better features to improve the accuracy without the need of more powerful hardware resources. In this paper, we propose a hybrid pooling method that incorporates multiresolution analysis within the CNN layers to reduce the feature map size without losing details. To prevent relevant information from losing during the downsampling process an existing pooling method is combined with wavelet transform technique, keeping those details "alive" and enriching other stages of the CNN. Achieving better quality characteristics improves CNN accuracy. To validate this study, ten pooling methods, including the proposed model, are tested using four benchmark datasets. The results are compared with four of the evaluated methods, which are also considered as the state-of-the-art.

scholarly journals Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks

2020 ◽  
Author(s):  
Tuan Hoang ◽  
Thanh-Toan Do ◽  
Tam V. Nguyen ◽  
Ngai-Man Cheung
Keyword(s):  
Neural Networks ◽  
Cost Function ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Gradient Descent ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Deep Convolutional Neural Networks ◽  
Novel Method ◽  
The Cost

This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. However, this approach would result in some mismatch: the gradient descent updates full-precision weights, but it does not update the quantized weights. To address this issue, we propose a novel method that enables direct updating of quantized weights with learnable quantization levels to minimize the cost function using gradient descent. Second, to obtain low bit-width activations, existing works consider all channels equally. However, the activation quantizers could be biased toward a few channels with high-variance. To address this issue, we propose a method to take into account the quantization errors of individual channels. With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the image classification task, using AlexNet, ResNet and MobileNetV2 architectures on CIFAR-100 and ImageNet datasets.

scholarly journals Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

2018 ◽  
Author(s):  
Yang He ◽  
Guoliang Kang ◽  
Xuanyi Dong ◽  
Yanwei Fu ◽  
Yi Yang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
The State ◽  
Training Data ◽  
Deep Convolutional Neural Networks ◽  
Inference Procedure ◽  
Accuracy Improvement ◽  
Large Capacity ◽  
Pruning Methods

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pretrained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/softfilter-pruning

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

Sign in / Sign up

Export Citation Format

Share Document