Convolutional Neural Networks with Recurrent Neural Filters

Yang, Yi

doi:10.18653/v1/d18-1109

Cited by 27 publications

(27 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wang et al [27] further introduced the discrete cosine transform (DCT) bases and converted convolution filters into the frequency domain to achieve higher compression and speed-up ratios. Yang et al [28] used a set of Lego filters to build efficient CNNs.…”

Section: Data-driven Network Compressionmentioning

confidence: 99%

Data-Free Learning of Student Networks

Chen

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

307

245

View full text Add to dashboard Cite

Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training compact deep models, when we can directly access the training dataset. However, training data for the given deep network are often unavailable due to some practice problems (e.g. privacy, legal issue, and transmission), and the architecture of the given network are also unknown except some interfaces. To this end, we propose a novel framework for training efficient deep neural networks by exploiting generative adversarial networks (GANs). To be specific, the pre-trained teacher networks are regarded as a fixed discriminator and the generator is utilized for derivating training samples which can obtain the maximum response on the discriminator. Then, an efficient network with smaller model size and computational complexity is trained using the generated data and the teacher network, simultaneously. Efficient student networks learned using the proposed Data-Free Learning (DAFL) method achieve 92.22% and 74.47% accuracies using ResNet-18 without any training data on the CIFAR-10 and CIFAR-100 datasets, respectively. Meanwhile, our student network obtains an 80.56% accuracy on the CelebA benchmark.

show abstract

Section: Data-driven Network Compressionmentioning

confidence: 99%

Data-Free Learning of Student Networks

Chen

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

307

245

View full text Add to dashboard Cite

show abstract

“…On the ImageNet dataset, this network can achieve a better classification effect with lower computational cost. LegoNet [28] designs the new filter modules that are assembled by a set of shared Lego filters, which are usually much smaller in size. Using the LegoNet as part of the network structure can reduce parameters and speed up the network.…”

Section: Related Workmentioning

confidence: 99%

A new lightweight network based on MobileNetV3

2022

KSII TIIS

View full text Add to dashboard Cite

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

show abstract

“…Wang et al [19] proposed RNN-Capsule, a capsule model based on recurrent neural network (RNN) for sentiment analysis. Yang [20] presented RNFs, a new class of convolution filters based on recurrent neural networks. McCann et al [21] introduced an approach for transferring knowledge from an encoder pretrained on machine translation to a variety of downstream natural language processing (NLP) tasks.…”

Section: Literature Reviewmentioning

confidence: 99%

MTVRep: A movie and TV show reputation system based on fine-grained sentiment and semantic analysis

Benlahbib

Nfaoui

2021

IJECE

View full text Add to dashboard Cite

Customer reviews are a valuable source of information from which we can extract very useful data about different online shopping experiences. For trendy items (products, movies, TV shows, hotels, services . . . ), the number of available users and customers’ opinions could easily surpass thousands. Therefore, online reputation systems could aid potential customers in making the right decision (buying, renting, booking . . . ) by automatically mining textual reviews and their ratings. This paper presents MTVRep, a movie and TV show reputation system that incorporates fine-grained opinion mining and semantic analysis to generate and visualize reputation toward movies and TV shows. Differently from previous studies on reputation generation that treat the task of sentiment analysis as a binary classification problem (positive, negative), the proposed system identifies the sentiment strength during the phase of sentiment classification by using fine-grained sentiment analysis to separate movie and TV show reviews into five discrete classes: strongly negative, weakly negative, neutral, weakly positive and strongly positive. Besides, it employs embeddings from language models (ELMo) representations to extract semantic relations between reviews. The contribution of this paper is threefold. First, movie and TV show reviews are separated into five groups based on their sentiment orientation. Second, a custom score is computed for each opinion group. Finally, a numerical reputation value is produced toward the target movie or TV show. The efficacy of the proposed system is illustrated by conducting several experiments on a real-world movie and TV show dataset.

show abstract

Convolutional Neural Networks with Recurrent Neural Filters

Cited by 27 publications

References 9 publications

Data-Free Learning of Student Networks

Data-Free Learning of Student Networks

A new lightweight network based on MobileNetV3

MTVRep: A movie and TV show reputation system based on fine-grained sentiment and semantic analysis

Contact Info

Product

Resources

About