Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture

Liang, Jinhua; Zhang, Tao; Guo, Feng

doi:10.1109/access.2020.3015714

Cited by 19 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 12, the recognition results of several comparison models are shown. The different colors indicate CRNN (Convolutional and Recurrent Neural Network) (Hu et al, 2023), DBNs (Deep Belief Networks) (Yang et al, 2018), Swin-Transformer (Chen et al, 2022), SAEs (Sparse Autoencoders) (Ke et al, 2018), and MobileNet (Mobile Network) (Liang et al, 2020) respectively. The primary parameters for the comparative models are comprehensively listed in Table 3.…”

Section: Figurementioning

confidence: 99%

DWSTr: a hybrid framework for ship-radiated noise recognition

Wang,

Zhang,

Huang

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

The critical nature of passive ship-radiated noise recognition for military and economic security is well-established, yet its advancement faces significant obstacles due to the complex marine environment. The challenges include natural sound interference and signal distortion, complicating the extraction of key acoustic features and ship type identification. Addressing these issues, this study introduces DWSTr, a novel method combining a depthwise separable convolutional neural network with a Transformer architecture. This approach effectively isolates local acoustic features and captures global dependencies, enhancing robustness against environmental interferences and signal variability. Validated by experimental results on the ShipsEar dataset, DWSTr demonstrated a notable 96.5\% recognition accuracy, underscoring its efficacy in accurate ship classification amidst challenging conditions. The integration of these advanced neural architectures not only surmounts existing barriers in noise recognition but also offers computational efficiency for real-time analysis, marking a significant advancement in passive acoustic monitoring and its application in strategic and economic contexts.

show abstract

Section: Figurementioning

confidence: 99%

DWSTr: a hybrid framework for ship-radiated noise recognition

Wang,

Zhang,

Huang

et al. 2024

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…Recent works on ASC performed the popular low-level feature extraction methods such as Log-Mel scale [8,21,24,28,36], Constant-Q transform spectrograms [3]. While Mel spectrogram feature uses as a most used method for acoustic signal process, several pre-processing techniques are also performed various aspects of an acoustic scene.…”

Section: Related Workmentioning

confidence: 99%

Acoustic Scene Classification using Attention based Deep Learning Model

2022

IJIES

View full text Add to dashboard Cite

Acoustic scene classification is a difficult issue among artificial intelligence, signal processing, and machine learning. Scene recognition performance has a robust relation with feature learning using deep convolutional networks.In the following research, end-to-end deep residual network embedded channel attention is explored to learn the discriminative features from the audio scene. Log-Mel spectrogram is obtained from input raw audios. It is forwarded to proposed attention network. An extracted feature layer is concatenated with the SoftMax classifier in the proposed attention network. The experimentation is carried out on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 and 2017 datasets. The proposed channel-attention-based residual network achieves classification results with an average accuracy of 80.27% and 80.82%, respectively.

show abstract

“…The second is to transfer the knowledge from large-scale pre-trained model to a small model via knowledge distillation [13,14,15]. The last one is to directly exploit efficient networks for audio classification, such as MobileNets [7,16]. In summary, these methods mainly focus on reducing model size.…”

Section: Introductionmentioning

confidence: 99%

Simple Pooling Front-Ends for Efficient Audio Classification

Liu

Kong³

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Recently, there has been increasing interest in building efficient audio neural networks for on-device scenarios. Most existing approaches are designed to reduce the size of audio neural networks using methods such as model pruning. In this work, we show that instead of reducing model size using complex methods, eliminating the temporal redundancy in the input audio features (e.g., mel-spectrogram) could be an effective approach for efficient audio classification. To do so, we proposed a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information within the mel-spectrogram. We perform extensive experiments on four audio classification tasks to evaluate the performance of SimPFs. Experimental results show that SimPFs can achieve a reduction in more than half of the number of floating point operations (FLOPs) for off-the-shelf audio neural networks, with negligible degradation or even some improvements in audio classification performance.

show abstract

Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture

Cited by 19 publications

References 22 publications

DWSTr: a hybrid framework for ship-radiated noise recognition

DWSTr: a hybrid framework for ship-radiated noise recognition

Acoustic Scene Classification using Attention based Deep Learning Model

Simple Pooling Front-Ends for Efficient Audio Classification

Contact Info

Product

Resources

About