FSRFNet: Feature-selective and Spatial Receptive Fields Networks
Source abstract
Abstract
The attention mechanism plays a crucial role in the human visual experience. In the cognitive neuroscience community, the receptive field size of visual cortical neurons is regulated by the additive effect of feature-selective and spatial attention. We propose a novel architectural unit called a “Feature-selective and Spatial Receptive Fields” (FSRF) block that implements adaptive receptive field sizes of neurons through the additive effects of feature-selective and spatial attention. We show that FSRF blocks can be inserted into the architecture of existing convolutional neural networks to form an FSRF network architecture, and test its generalization capabilities on different datasets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Visual perception and processing mechanisms · Neural dynamics and brain function · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai 201418, China
References (60)
Show source-provided references
1. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
2. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
3. Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv.
4. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
5. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (February, January USA). Inception-v4, Inception-ResNet and the impact of residual connections on learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, California.
6. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
7. Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.10.5244/C.30.87 ↗
8. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–8). ImageNet classification with deep convolutional neural networks. Proceedings of the Neural Information Processing Systems (NIPS), Harrahs and Harveys, Lake Tahoe, CA, USA.
9. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
10. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
11. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., and Adam, H. (2017). MobileNet: Efficient convolutional neural networks for mobile vision applications. arXiv.
12. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
13. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
14. Selective search for object recognition10.1007/s11263-013-0620-5 ↗
15. Support vector networks10.1007/BF00994018 ↗
16. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
17. Girshick, R. (2015, January 8–10). Fast r-cnn. Deformable part models are convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision, Boston, MA, USA.10.1109/CVPR.2015.7298641 ↗
18. Ren, S., He, K., and Girshick, R. (2015, January 7–12). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the International Conference on Neural Information Processing Systems, Cambridge, MA, USA.
19. Redmon, J., Divvala, S., and Girshick, R. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
20. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 8–16). SSD: Single Shot MultiBox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
21. Redmon, J., and Farhadi, A. (2017, January 21–26). Yolo 9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
22. Redmon, J., and Farhadi, A. (2018). Yolo v3: An incremental improvement. arXiv.
23. Mnih, V., Heess, N., and Graves, A. (2014, January 8–13). Recurrent models of visual attention. Proceedings of the Neural Information Processing Systems (NIPS), Montréal, QC, Canada.
24. Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., and Bengio, Y. (2015, January 6–11). Show, attend and tell: Neural image caption generation with visual attention. Proceedings of the 32nd International Conference on Machine Learning, Lille, France.
25. Jaderberg, M., Simonyan, K., and Zisserman, A. (2015, January 8–13). Spatial transformer networks. Proceedings of the Neural Information Processing Systems (NIPS), Montréal, QC, Canada.
26. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex10.1113/jphysiol.1962.sp006837 ↗
27. Attentional control of visual perception: Cortical and subcortical mechanisms10.1101/SQB.1990.055.01.090 ↗
28. Orientation-selective inhibition from beyond the classic visual receptive field10.1016/0006-8993(78)90937-X ↗
29. Time course of attention reveals different mechanisms for spatial and feature-based attention in area V410.1016/j.neuron.2005.07.020 ↗
30. Neural integration of top-down spatial and feature-based information in visual search10.1523/JNEUROSCI.1262-08.2008 ↗
31. Effects of feature-selective and spatial attention at different stages of visual processing10.1162/jocn.2009.21328 ↗
32. Interaction between spatial and feature attention in posterior parietal cortex10.1016/j.neuron.2016.07.025 ↗
33. Li, X., Wang, W., Hu, X., and Yang, J. (2019, January 15–21). Selective Kernel Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR.2019.00060 ↗
34. Radar emission sources identification based on hierarchical agglomerative clustering for large data sets10.1155/2016/1879327 ↗
35. Matuszewski, J. (2018, January 20–24). Radar signal identification using a neural network and pattern recognition methods. Proceedings of the 14th International Conference on Advanced Trends in Radioelectionics, Telecommunications and Computer Engineering (TCSET 2018), Lviv-Slavsk, Ukraine.10.1109/TCSET.2018.8336160 ↗
36. Dudczyk, J., and Wnuk, M. (2004, January 12–14). The utilization of unintentional radiation for identification of the radiation sources. Proceedings of the 34 European Microwave Conference (EuMC 2004), Amsterdam, The Netherlands.
37. Matuszewski, J., and Pietrow, D. (2018, January 19–21). Recognition of electromagnetic sources with the use of deep neural networks. Proceedings of the XII Conference on Reconnaissance and Electronic Warfare Systems, Oltarzew, Poland.10.1117/12.2524536 ↗
38. Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8–14). ShuffleNet v2: Practical guidelines for efficient CNN architecture design. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
39. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–22). MobileNet v2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
40. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
41. Computational modelling of visual attention10.1038/35058500 ↗
42. A model of saliency-based visual attention for rapid scene analysis10.1109/34.730558 ↗
43. Larochelle, H., and Hinton, G.E. (2010, January 6–11). Learning to combine foveal glimpses with a third-order Boltzmann machine. Proceedings of the Neural Information Processing Systems (NIPS), Vancouver, WA, Canada.
44. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv.
45. You, Q., Jin, H., Wang, Z., Fang, C., and Luo, J. (2016, January 27–30). Image captioning with semantic attention. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.503 ↗
46. Chung, J.S., Senior, A., Vinyals, O., and Zisserman, A. (2017, January 21–26). Lip reading sentences in the wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.367 ↗
47. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
48. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
49. Focal attention produces spatially selective processing in visual cortical areas V1, V2, and V4 in the presence of competing stimuli10.1152/jn.1993.70.3.909 ↗
50. Neural mechanisms of spatial selective attention in areas V1, V2, and V4 of macaque visual cortex10.1152/jn.1997.77.1.24 ↗
51. Mechanisms of visual attention in the human cortex10.1146/annurev.neuro.23.1.315 ↗
52. The relationship between synchronization among neuronal populations and their mean activity levels10.1162/089976699300016287 ↗
53. Enhanced spatial focusing increases feature-based selection in unattended locations10.1038/s41598-018-34424-5 ↗
54. Tiny imagenet classification with convolutional neural networks
55. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–12). Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. Proceedings of the IEEE Conference on Computer Vision, Boston, MA, USA.10.1109/ICCV.2015.123 ↗
56. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–22). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE International Conference on Computer Vision, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
57. Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images (Technical Report), University of Toronto.
58. Lin, M., Qiang, C., and Shuicheng, Y. (2013). Network in network. arXiv.
59. Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K.Q. (2016, January 8–16). Deep networks with stochastic depth. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_39 ↗
60. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 21–26). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Honolulu, HI, USA.10.1109/ICCV.2017.74 ↗