Fetching the paper…
Reading the bibliography…
The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished.
Learning imbalanced datasets with label-distribution-aware margin loss, 2019
Cao, K., Wei, C., Gaidon, A., Arechiga, N., and Ma, T · 1906
Earlier work this paper cites.
Decoupling representation and classifier for long-tailed recognition, 2019
Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., and Kalantidis, Y · 1910
Earlier work this paper cites.
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., and White, H · 1989
Earlier work this paper cites.
Approximation capabilities of multilayer feedforward networks
Hornik, K · 1991
Earlier work this paper cites.
Revealing the structure of deep neural networks via convex duality, 2020
Ergen, T. and Pilanci, M · 2002
Earlier work this paper cites.
Prevalence of neural collapse during the terminal phase of deep learning training
Papyan, V., Han, X. Y., and Donoho, D. L · 2008
Earlier work this paper cites.
Neural collapse with cross-entropy loss, 2020
Lu, J. and Steinerberger, S · 2012
Earlier work this paper cites.
Very deep convolutional networks for large-scale image recognition, 2014
Simonyan, K. and Zisserman, A · 2014
Earlier work this paper cites.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Earlier work this paper cites.
Learning deep representation for imbalanced classification
Huang, C., Li, Y., Loy, C. C., and Tang, X · 2016
Earlier work this paper cites.
Universal approximations of invariant maps by neural networks, 2018
Yarotsky, D · 2018
Earlier work this paper cites.
Universality of deep convolutional neural networks, 2018
Zhou, D.-X · 2018
Cited alongside, same era.
Exploring balanced feature spaces for representation learning
Kang, B., Li, Y., Xie, S., Yuan, Z., and Feng, J · 2020
Cited alongside, same era.
Adjusting decision boundary for class imbalanced learning
Kim, B. and Kim, J · 2020
Cited alongside, same era.
Identifying and compensating for feature deviation in imbalanced deep learning
Ye, H.-J., Chen, H.-Y., Zhan, D.-C., and Chao, W.-L · 2020
Cited alongside, same era.
Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training
Fang, C., He, H., Long, Q., and Su, W. J · 2021
Cited alongside, same era.
Extended unconstrained features model for exploring deep neural collapse, 2022
Tirer, T. and Bruna, J · 2022
Later among the works it cites.
Yang, Y., Chen, S., Li, X., Xie, L., Lin, Z., and Tao, D · 2022
Later among the works it cites.
On the implicit geometry of cross-entropy parameterizations for label-imbalanced data
Behnia, T., Kini, G. R., Vakilian, V., and Thrampoulidis, C · 2023
Later among the works it cites.
Neural collapse in deep linear network: From balanced to imbalanced data
Dang, H., Nguyen, T., Tran, T., Tran, H., and Ho, N · 2023
Later among the works it cites.
Dissecting supervised contrastive learning, 2023
Graf, F., Hofer, C. D., Niethammer, M., and Kwitt, R · 2023
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Han, X. Y., Papyan, V., and Donoho, D. L · 2021
Cited alongside, same era.
An unconstrained layer-peeled perspective on neural collapse, 2021
Ji, W., Lu, Y., Zhang, Y., Deng, Z., and Su, W. J · 2021
Cited alongside, same era.
A geometric analysis of neural collapse with unconstrained features
Zhu, Z., Ding, T., Zhou, J., Li, X., You, C., Sulam, J., and Qu, Q · 2021
Cited alongside, same era.
Memorization-dilation: Modeling neural collapse under noise
Nguyen, D. A., Levie, R., Lienen, J., Hüllermeier, E., and Kutyniok, G · 2022
Cited alongside, same era.
Neural collapse in deep homogeneous classifiers and the role of weight decay
Rangamani, A. and Banburski-Fahey, A · 2022
Cited alongside, same era.
Imbalance trouble: Revisiting neural-collapse geometry, 2022
Thrampoulidis, C., Kini, G. R., Vakilian, V., and Behnia, T · 2022
Cited alongside, same era.
Zhou, J., Li, X., Ding, T., You, C., Qu, Q., and Zhu, Z
Cited in the paper.
Later among the works it cites.
Neural collapse for unconstrained feature model under cross-entropy loss with imbalanced data
Hong, W. and Ling, S · 2023
Later among the works it cites.
Supervised-contrastive loss learns orthogonal frames and batching matters
Kini, G. R., Vakilian, V., Behnia, T., Gill, J., and Thrampoulidis, C · 2023
Later among the works it cites.
Inducing neural collapse in deep long-tailed learning
Liu, X., Zhang, J., Hu, T., Cao, H., Yao, Y., and Pan, L · 2023
Later among the works it cites.
Deep neural collapse is provably optimal for the deep unconstrained features model
Súkeník, P., Mondelli, M., and Lampert, C · 2023
Later among the works it cites.
Perturbation analysis of neural collapse
Tirer, T., Huang, H., and Niles-Weed, J · 2023
Later among the works it cites.