Transform-Based Feature Map Compression for CNN Inference

Shi, Yubo; Wang, Meiqi; Chen, Siyi; Wei, Jinghe; Wang, Zhongfeng

doi:10.1109/iscas51556.2021.9401133

Cited by 12 publications

(3 citation statements)

References 35 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these methods, conversion, quantization, and encryption are manually designed and not optimally designed, which poses a challenge to the compression of images. Several techniques such as predictive coding [19], transform-based coding [20], and VQ have been proposed for image compression. VQ-based image compression techniques are used as popular techniques for high-level, low-distortion compression compared to other methods.…”

Section: Related Workmentioning

confidence: 99%

Compression of images with a mathematical approach based on sine and cosine equations and vector quantization (VQ)

Ghadami

Rahebi

2023

Soft Comput

View full text Add to dashboard Cite

Image compression is one of the most attractive and practical topics. Without image compression, the image size becomes too large for storage. The transmission of uncompressing images on computer networks slows down and network bandwidth is wasted. Various approaches to image compression have been proposed so far, one of which is vector quantization using mathematical concepts and image processing to compress images. The LBG algorithm is a practical algorithm for compressing images using vector quantization concepts. Most researchers have used metaheuristic and optimization algorithms with a modeling approach of swarm behavior of living things to improve the quality of the LBG compression algorithm. This study uses a meta-heuristic method based on sine and cosine algorithms (SCA) to improve the quality of the image compression algorithm. In the proposed mathematical modeling method, the SCA algorithm is improved using spiral equations. The improved SCA algorithm is then used to find the optimal codebook in the LBG compression algorithm. Finding a better codebook in the proposed method will increase the quality of the compression images. The proposed method implemented in MATLAB software and experiments showed that the PSNR index in the proposed method improve the ratio of the LBG algorithm by about 13.73%. Evaluations show that the PSNR index of compressed images in the proposed method is higher and better than PBM, CS-LBG, FA-LBG, BA-LBG, HBMO-LBG, QPSO-LBG, PSO-LBG. The result shows the proposed method (or ISCA-LBG) has less time complexity than HHO and WOA compression algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Compression of images with a mathematical approach based on sine and cosine equations and vector quantization (VQ)

Ghadami

Rahebi

2023

Soft Comput

View full text Add to dashboard Cite

show abstract

“…FCL maintains the same number of channels while fusing global context information features [36]. Applying the GC layer in neural networks enhances the model's comprehension of the overall image and utilization of context information [37]. The principle of the GC layer is represented as follows:…”

Section: Bfamentioning

confidence: 99%

CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer

Hu,

Gao,

Yang

et al. 2023

Mathematics

View full text Add to dashboard Cite

Glass plays a vital role in several fields, making its accurate detection crucial. Proper detection prevents misjudgments, reduces noise from reflections, and ensures optimal performance in other computer vision tasks. However, the prevalent usage of glass in daily applications poses unique challenges for computer vision. This study introduces a novel convolutional attention glass segmentation network (CAGNet) predicated on a transformer architecture customized for image glass detection. Based on the foundation of our prior study, CAGNet minimizes the number of training cycles and iterations, resulting in enhanced performance and efficiency. CAGNet is built upon the strategic design and integration of two types of convolutional attention mechanisms coupled with a transformer head applied for comprehensive feature analysis and fusion. To further augment segmentation precision, the network incorporates a custom edge-weighting scheme to optimize glass detection within images. Comparative studies and rigorous testing demonstrate that CAGNet outperforms several leading methodologies in glass detection, exhibiting robustness across a diverse range of conditions. Specifically, the IOU metric improves by 0.26% compared to that in our previous study and presents a 0.92% enhancement over those of other state-of-the-art methods.

show abstract

“…[8] developed a feature channel arrangement method for the image/video-codec based feature compression framework. [9] explored transform (i.e., DCT) for more efficient intermediate deep feature compression.…”

Section: Introduction Compression For Intermediate Deep Learning Feat...mentioning

confidence: 99%

Channel-Wise Bit Allocation for Deep Visual Feature Quantization

Wang

Chen

Wang

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Intermediate deep visual feature compression and transmission is an emerging research topic, which enables a good balance among computing load, bandwidth usage and generalization ability for AI-based visual analysis in edge-cloud collaboration. Quantization and the corresponding ratedistortion optimization are the key techniques in deep feature compression. In this paper, by exploring the feature statistics and a greedy iterative algorithm, we propose a channel-wise bit allocation method for deep feature quantization optimizing for network output error. Given the limited rate and computational power, the proposed method can quantize features with small information loss. Moreover, the method also provides the option to handle the trade-offs between computational cost and quantization performance. Experimental results on ResNet and VGGNet features demonstrate the effectiveness of the proposed bit allocation method.

show abstract

Transform-Based Feature Map Compression for CNN Inference

Cited by 12 publications

References 35 publications

Compression of images with a mathematical approach based on sine and cosine equations and vector quantization (VQ)

Compression of images with a mathematical approach based on sine and cosine equations and vector quantization (VQ)

CAGNet: A Multi-Scale Convolutional Attention Method for Glass Detection Based on Transformer

Channel-Wise Bit Allocation for Deep Visual Feature Quantization

Contact Info

Product

Resources

About