[1] SIMONYAN K, ZISSERMAN A. Very deep
convolutional networks for large-scale image
recognition[C] //Proceedings of International Conference
on Learning Representations. San Diego, CA, USA: IEEE
Press, 2015: 2242-2251.
[2] HE K, ZHANG X, REN S, et al. Deep residual
learning for image recognition[C] //Proceedings of IEEE
International Conference on Computer Vision and Pattern
Recognition. Las Vegas, NV, USA: IEEE Computer
Society, 2016: 770-778.
[3] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:
Towards real-time object detection with region proposal
networks[J]. IEEE Transactions on Pattern Analysis and
Machine Intelligence, 2017, 39(6): 1137-1149.
[4] YAN C, ZHANG H, LI X, et al. R-SSD: Refined
single shot multi-box detector for pedestrian detection[J].
Applied Intelligence, 2022, 52(9): 10430-10447.
[5] LIU Q, KORTYLEWSKI A, ZHANG Z, et al.
Learning part segmentation through unsupervised domain
adaptation from synthetic vehicles[C] //Proceedings of
IEEE International Conference on Computer Vision and
Pattern Recognition. New Orleans, LA, USA: IEEE
Computer Society, 2022: 19118-19129.
[6] PENG D, LEI Y, HAYAT M, et al. Semantic-aware
domain generalized segmentation[C] //Proceedings of
IEEE International Conference on Computer Vision and
Pattern Recognition. New Orleans, LA, USA: IEEE
Computer Society, 2022: 2584-2595.
[7] ZHOU E, XU X, XU B, et al. An enhancement model
based on dense aurous and inception convolution for
image semantic segmentation[J]. Applied Intelligence,
2023, 53(5): 5519-5531.
[8] 司念文, 张文林, 屈丹, 等. 卷积神经网络表征可
视 化 研 究 综 述 [J]. 自 动 化 学 报 , 2022, 48(08):
1890-1920.
SI N W, ZHANG W L, QU D, et al. Representation
visualization of convolutional neural networks: A
survey[J]. Acta Automatica Sinical, 2022, 48(8):
1890-1892. (in Chinese)
[9] EHSAN U, WINTERSBERGER P, LIAO Q V, et al.
Human-centered explainable AI: Beyond opening the
black-box of AI[C] //Proceedings of International
Conference on Human Factors in Computing Systems.
Long Beach, CA, USA: ACM Press, 2022: 1009-1020.
[10] GLOROT X, BENGIO Y. Understanding the
difficulty of training deep feedforward neural networks[C]
//Proceedings of International Conference on Artificial
Intelligence and Statistics. Sardinia, Italy: Microtome
Publishing, 2010: 249-256.
[11] HUANG G, LIU Z, VAN DER MAATEN L, et al.
Densely connected convolutional networks[C]
//Proceedings of IEEE International Conference on
Computer Vision and Pattern Recognition. Honolulu, HI,
USA: IEEE Computer Society, 2017: 2261-2269.
[12] MOHAMED E, SIRLANTZIS K, HOWELLS G. A
review of visualization and explanation techniques for
convolutional neural networks and their evaluation[J].
Displays, 2022, 73(5): 1245-1258.
[13] NGUYEN A, YOSINSKI J, CLUNE J.
Understanding neural networks via feature visualization:
A Survey [M]. Cambridge, USA: MIT Press, 2019.
[14] OYEDOTUN O K, EL RAHMAN SHABAYEK A,
AOUADA D, et al. Training very deep networks viaresidual learning with stochastic input shortcut
connections[C] //Proceedings of International Conference
on Neural Information Processing. Guangzhou, China:
Springer Verlag, 2017: 23-33.
[15] OYEDOTUN O K, ISMAEIL K A, AOUADA D.
Why is everyone training very deep neural network with
skip connections?[J]. IEEE Transactions on Neural
Networks and Learning Systems, 2023, 34(9): 5961-5975.
[16] IOFFE S, SZEGEDY C. Batch normalization:
Accelerating deep network training by reducing internal
covariate shift[C] //Proceedings of International
Conference on Machine Learning. Lile, France: IEEE
Press, 2015: 448-456.
[17] CHEN Y, LI J, XIAO H, et al. Dual path networks[C]
//Proceedings of Annual Conference on Neural
Information Processing Systems. Long Beach, CA, USA:
NIPS Foundation, 2017: 4468-4476.
[18] ZHANG X, LI Z, LOY C C, et al. PolyNet: A pursuit
of structural diversity in very deep networks[C]
//Proceedings of IEEE International Conference on
Computer Vision and Pattern Recognition. Honolulu, HI,
USA: IEEE Computer Society, 2017: 3900-3908.
[19] SZEGEDY C, IOFFE S, VANHOUCKE V, et al.
Inception-v4, Inception-ResNet and the impact of residual
connections on learning[C] //Proceedings of AAAI
Conference on Artificial Intelligence. San Francisco, CA,
USA: AAAI Press, 2017: 4278-4284.
[20] VASWANI A, SHAZEER N, PARMAR N, et al.
Attention is all you need[C] //Proceedings of Annual
Conference on Neural Information Processing Systems.
Long Beach, CA, USA: NIPS Foundation, 2017:
5999-6009.
[21] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et
al. An Image is worth 16×16 words: Transformers for
image recognition at scale[C] //Proceedings of
International Conference on Learning Representations.
Washington D. C., USA: IEEE Press, 2021: 5278-5284.
[22] DAI D, LI Y, WANG Y, et al. Rethinking the image
feature biases exhibited by deep convolutional neural
network models in image recognition[J]. CAAI
Transactions on Intelligence Technology, 2022, 7(4):
721-731.
[23] FONG R C, VEDALDI A. Interpretable explanations
of black boxes by meaningful perturbation[C]
//Proceedings of IEEE International Conference on
Computer Vision. Venice, Italy: IEEE Press, 2017:
3449-3457.
[24] FONG R, PATRICK M, VEDALDI A.
Understanding deep networks via extremal perturbations
and smooth masks[C] //Proceedings of IEEE International
Conference on Computer Vision. Seoul, Republic of
Korea: IEEE Press, 2019: 2950-2958.v
[25] ZEILER M D, FERGUS R. Visualizing and
understanding convolutional networks[C] //Proceedings
of European Conference on Computer Vision. Zurich,
Switzerland: Springer Verlag, 2014: 818-833.
[26] SMILKOV D, THORAT N, KIM B, et al.
SmoothGrad: Removing noise by adding noise[J]. IEEE
Transactions on Multimedia, 2019, 20(8): 2323-2334.
[27] SUNDARARAJAN M, TALY A, YAN Q. Axiomatic
attribution for deep networks[C] //Proceedings of
International Conference on Machine Learning. Sydney,
NSW, Australia: IEEE Press, 2017: 5109-5118.
[28] KIM B, SEO J, JEON S, et al. Why are saliency
maps noisy solution to noisy saliency maps[C]
//Proceedings of IEEE International Conference on
Computer Vision Workshops. Seoul, Republic of Korea:
IEEE Press, 2019: 4149-4157.
[29] GU J, YANG Y, TRESP V. Understanding individual
decisions of CNNs via contrastive backpropagation[C]
//Proceedings of Asian Conference on Computer Vision.
Perth, WA, Australia: Springer Verlag, 2019: 119-134.
[30] IWANA B K, KUROKI R, UCHIDA S. Explaining
convolutional neural networks using softmax gradient
layer-wise relevance propagation[C] //Proceedings ofIEEE International Conference on Computer Vision
Workshops. Seoul, Republic of Korea: IEEE Press, 2019:
4176-4185.
[31] SELVARAJU R R, COGSWELL M, DAS A, et al.
Grad-CAM: Visual explanations from deep networks via
gradient-based localization[J]. International Journal of
Computer Vision, 2020, 128(2): 336-359.
[32] SHI T, LI Y, LIANG H, et al. Score-CAM: Class
activation map based on logarithmic transformation[C]
//Proceedings of IEEE International Conference on Signal
Processing. Beijing, China: IEEE Press, 2022: 256-259.
[33] MONTAVON G, LAPUSCHKIN S, BINDER A, et
al. Explaining nonlinear classification decisions with deep
Taylor decomposition[J]. Pattern Recognition, 2017, 65:
211-222.
[34] YOSINSKI J, CLUNE J, NGUYEN A, et al.
Understanding neural networks through deep
visualization[J]. Neural Networks, 2015, 34: 345-356.
[35] WANG F, LIU H, CHENG J. Visualizing deep neural
network by alternately image blurring and deblurring[J].
Neural Networks, 2018, 97: 162-172.
[36] SHI R, LI T, YAMAGUCHI Y. Group visualization
of class-discriminative features[J]. Neural Networks,
2020, 129: 75-90.
[37] KATZMANN A, TAUBMANN O, AHMAD S, et al.
Explaining clinical decision support systems in medical
imaging using cycle-consistent activation
maximization[J]. Neurocomputing, 2021, 458: 141-156.
[38] MAHENDRAN A, VEDALDI A. Understanding
deep image representations by inverting them[C]
//Proceedings of IEEE International Conference on
Computer Vision and Pattern Recognition. Boston, MA,
USA: IEEE Computer Society, 2015: 5188-5196.
[39] DENG J, DONG W, SOCHER R, et al. ImageNet: A
large-scale hierarchical image database[C] //Proceedings
of IEEE International Conference on Computer Vision
and Pattern Recognition. Miami, FL, USA: IEEE
Computer Society, 2009: 248-255.
|