Fetching the paper…
Reading the bibliography…
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models.
Data augmentation for BERT fine-tuning in open-domain question answering
Yang, W., Xie, Y., Tan, L., Xiong, K., Li, M., and Lin, J · 1904
Earlier work this paper cites.
Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter, 2019
Sanh, V., Debut, L., Chaumond, J., and Wolf, T · 1910
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., and Hinton, G. E · 2012
Earlier work this paper cites.
Improving neural machine translation models with monolingual data
Sennrich, R., Haddow, B., and Birch, A · 2015
Earlier work this paper cites.
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A · 2015
Earlier work this paper cites.
Data recombination for neural semantic parsing
Jia, R. and Liang, P · 2016
Earlier work this paper cites.
Decoupled weight decay regularization, 2017
Loshchilov, I. and Hutter, F · 2017
Earlier work this paper cites.
Image classification of melanoma, nevus and seborrheic keratosis by deep neural network ensemble
Matsunaga, K., Hamada, A., Minagawa, A., and Koga, H · 2017
Earlier work this paper cites.
Pixeldefend: Leveraging generative models to understand and defend against adversarial examples
Song, Y., Kim, T., Nowozin, S., Ermon, S., and Kushman, N · 2017
Earlier work this paper cites.
Test-time data augmentation for estimation of heteroscedastic aleatoric uncertainty in deep neural networks
Ayhan, M. S. and Berens, P · 2018
Earlier work this paper cites.
Using wikipedia edits in low resource grammatical error correction
Boyd, A · 2018
Earlier work this paper cites.
Deflecting adversarial attacks with pixel deflection
Prakash, A., Moran, N., Garber, S., DiLillo, A., and Storer, J · 2018
Cited alongside, same era.
Understanding measures of uncertainty for adversarial example detection
Smith, L. and Gal, Y · 2018
Cited alongside, same era.
Good-enough compositional data augmentation
Andreas, J · 2019
Cited alongside, same era.
Nuanced metrics for measuring unintended bias with real data for text classification
Borkan, D., Dixon, L., Sorensen, J., Thain, N., and Vasserman, L · 2019
Cited alongside, same era.
Certified adversarial robustness via randomized smoothing
Cohen, J., Rosenfeld, E., and Kolter, Z · 2019
Cited alongside, same era.
Sequence-to-sequence pre-training with data augmentation for sentence rewriting
Zhang, Y., Ge, T., Wei, F., Zhou, M., and Sun, X · 2019
Later among the works it cites.
Transforming wikipedia into augmented data for query-focused summarization
Zhu, H., Dong, L., Wei, F., Qin, B., and Liu, T · 2019
Later among the works it cites.
An analysis of simple data augmentation for named entity recognition
Dai, X. and Adel, H · 2020
Later among the works it cites.
Daga: Data augmentation with a generation approach for low-resource tagging tasks
Ding, B., Liu, L., Bing, L., Kruengkrai, C., Nguyen, T. H., Joty, S., Si, L., and Miao, C · 2020
Later among the works it cites.
Grappa: grammar-augmented pre-training for table semantic parsing
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
An exploration of data augmentation and sampling techniques for domain-agnostic question answering
Longpre, S., Lu, Y., Tu, Z., and DuBois, C · 2019
Cited alongside, same era.
Abstract text summarization: A low resource challenge
Parida, S. and Motlicek, P · 2019
Cited alongside, same era.
Data augmentation via dependency tree morphing for low-resource languages
Şahin, G. G. and Steedman, M · 2019
Cited alongside, same era.
Xlda: Cross-lingual data augmentation for natural language inference and question answering
Singh, J., McCann, B., Keskar, N. S., Xiong, C., and Socher, R · 2019
Cited alongside, same era.
Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
Wang, G., Li, W., Aertsen, M., Deprest, J., Ourselin, S., and Vercauteren, T · 2019
Cited alongside, same era.
Generalized data augmentation for low-resource translation
Xia, M., Kong, X., Anastasopoulos, A., and Neubig, G · 2019
Cited alongside, same era.
Yu, T., Wu, C.-S., Lin, X. V., Wang, B., Tan, Y. C., Yang, X., Radev, D., Socher, R., and Xiong, C · 2020
Later among the works it cites.
A survey of data augmentation approaches for NLP
Feng, S. Y., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T., and Hovy, E. H · 2021
Later among the works it cites.
Wilds: A benchmark of in-the-wild distribution shifts
Koh, P. W., Sagawa, S., Marklund, H., Xie, S. M., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R. L., Gao, I., et al · 2021
Later among the works it cites.
Better aggregation in test-time augmentation
Shanmugam, D., Blalock, D., Balakrishnan, G., and Guttag, J · 2021
Later among the works it cites.
Controllable data synthesis method for grammatical error correction
Yang, L., Wang, C., Chen, Y., Du, Y., and Yang, E · 2022
Closest in time.
Data augmentation for low-resource neural machine translation
Fadaee, M., Bisazza, A., and Monz, C · 2090
Closest in time.