A Latency-Efficient Integration of Channel Attention for ConvNets
Source abstract
Abstract
Designing fast and accurate neural networks is becoming essential in various vision tasks. Recently, the use of attention mechanisms has increased, aimed at enhancing the vision task performance by selectively focusing on rel... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Speech and Audio Processing · Advanced Data Compression Techniques · Wireless Signal Modulation Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (53)
Show source-provided references
1. An improved deep fusion CNN for image recognition
2. A review on deep learning approaches to image classification and object segmentation
3. Review of nodule mineral image segmentation algorithms for deep-sea mineral resource assessment
4. Understanding batch normalization
5. Cbam: convolutional block attention module
6. Attention is all you need
7. An image is worth 16 × 16 words: transformers for image recognition at scale
8. Ba JL, Kiros JR, Hinton GE. Layer normalization. arXiv:160706450. 2016.
9. A convnet for the 2020s
10. Scaling up your kernels to 31 × 31: revisiting large kernel design in CNNs
11. GFNet: global filter networks for visual recognition10.1109/TPAMI.2023.3263824 ↗
12. Metaformer is actually what you need for vision
13. Howard AG. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:170404861. 2017.
14. Aggregated residual transformations for deep neural networks
15. Hornet: efficient high-order spatial interactions with recursive gated convolutions
16. Convnext v2: co-designing and scaling convnets with masked autoencoders
17. Imagenet: a large-scale hierarchical image database
18. Searching for mobilenetv3
19. Squeeze-and-excitation networks
20. Attention mechanisms in computer vision: a survey10.1007/s41095-022-0271-y ↗
21. Fcanet: frequency channel attention networks
22. ECA-Net: efficient channel attention for deep convolutional neural networks
23. Gated channel transformation for visual recognition
24. Imagenet classification with deep convolutional neural networks
25. Swin transformer: hierarchical vision transformer using shifted windows
26. Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv:211002178. 2021.
27. Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications
28. Mobile-former: bridging mobilenet and transformer
29. FastViT: a fast hybrid vision transformer using structural reparameterization
30. Rethinking vision transformers for mobilenet size and speed
31. Li J, Xia X, Li W, Li H, Wang X, Xiao X, et al. Next-vit: next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv:220705501. 2022.
32. Shazeer N. Fast transformer decoding: one write-head is all you need. arXiv:191102150. 2019.
33. Run, don’t walk: chasing higher FLOPS for faster neural networks
34. Dynamic relu
35. An n-sigmoid activation function to improve the squeeze-and-excitation for 2D and 3D deep networks10.3390/electronics12040911 ↗
36. Randaugment: practical automated data augmentation with a reduced search space
37. Mixup: beyond empirical risk minimization
38. Cutmix: regularization strategy to train strong classifiers with localizable features
39. Random erasing data augmentation
40. Rethinking the inception architecture for computer vision
41. Deep networks with stochastic depth
42. Going deeper with image transformers
43. Acceleration of stochastic approximation by averaging10.1137/0330046 ↗
44. Krizhevsky · Handbook of systemic autoimmune diseases · 2009
45. Automated flower classification over a large number of classes
46. 3D object representations for fine-grained categorization
47. Maji S, Kannala J, Rahtu E, Blaschko M, Vedaldi A. Fine-grained visual classification of aircraft. arXiv:1306.5151. 2013.
48. Ablation-cam: visual explanations for deep convolutional network via gradient-free localization
49. Microsoft coco: common objects in context
50. Mask R-CNN
51. Cascade R-CNN: delving into high quality object detection
52. Decoupled weight decay regularization
53. Wightman R. PyTorch Image Models. GitHub [Internet]; 2019. [cited 2025 Jan 14]. Available from: https://github.com/rwightman/pytorch-image-models.