본문 바로가기

Paper Review

Paper Review #21 - Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Paper Review 2022. 1. 2. Paper Review #21 - Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks - (2019.08.27) https://arxiv.org/abs/1908.10084 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed ..
Paper Review #20 - Better Fine-Tuning by Reducing Representational Collapse
Paper Review 2021. 12. 31. Paper Review #20 - Better Fine-Tuning by Reducing Representational Collapse Better Fine-Tuning by Reducing Representational Collapse - (2020.08.06) https://arxiv.org/abs/2008.03156 Better Fine-Tuning by Reducing Representational Collapse Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods. In this paper, we present a simplif..
Paper Review #19 - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Paper Review 2021. 12. 30. Paper Review #19 - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension - (19.10.29) https://arxiv.org/abs/1910.13461 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text..
Paper Review #18 - Unprocessing Images for Learned Raw Denoising
Paper Review 2021. 12. 30. Paper Review #18 - Unprocessing Images for Learned Raw Denoising Unprocessing Images for Learned Raw Denoising (18.11.27) - https://arxiv.org/abs/1811.11127 Unprocessing Images for Learned Raw Denoising Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to practical constrai arx..
Paper Review #17 - HINet: Half Instance Normalization Network for Image Restoration
Paper Review 2021. 12. 21. Paper Review #17 - HINet: Half Instance Normalization Network for Image Restoration HINet: Half Instance Normalization Network for Image Restoration (2021.05.13) - https://arxiv.org/abs/2105.06086 HINet: Half Instance Normalization Network for Image Restoration In this paper, we explore the role of Instance Normalization in low-level vision tasks. Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration..
Paper Review #16 - Aggregated Residual Transformations for Deep Neural Networks
Paper Review 2021. 11. 24. Paper Review #16 - Aggregated Residual Transformations for Deep Neural Networks Aggregated Residual Transformations for Deep Neural Networks (2017.04.11) https://arxiv.org/abs/1611.05431 Aggregated Residual Transformations for Deep Neural Networks We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design res..
Paper Review #15 - AutoAugment:Learning Augmentation Strategies from Data
Paper Review 2021. 10. 29. Paper Review #15 - AutoAugment:Learning Augmentation Strategies from Data AutoAugment:Learning Augmentation Strategies from Data (2019.04.11) https://arxiv.org/abs/1805.09501 AutoAugment: Learning Augmentation Policies from Data Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to a..
Paper Review #14 - Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations
Paper Review 2021. 10. 27. Paper Review #14 - Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations (2018.05.16) https://arxiv.org/abs/1805.06201 Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced wi..

티스토리툴바