paper-with-me

홈 › Papers

DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation

2022-06-07 · Sajad Norouzi, Rasa Hosseinzadeh, Felipe Perez, Maksims Volkovs

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease the number of required steps to reach a certain translation quality. The distilled model enjoys the computational benefits of early iterations while preserving the enhancements from several iterative steps. DiMS relies on two models namely student and teacher. The student is optimized to predict the output of the teacher after multiple decoding steps while the teacher follows the student via a slow-moving average. The moving average keeps the teacher's knowledge updated and enhances the quality of the labels provided by the teacher. During inference, the student is used for translation and no additional computation is added. We verify the effectiveness of DiMS on various models obtaining 7.8 and 12.9 BLEU points improvements in single-step translation accuracy on distilled and raw versions of WMT'14 De-En.

📄 PDF Abstract BibTeX arXiv:2206.02999

Code (1)

layer6ai-labs/dims 공식 구현 pytorch

Tasks

de-enMachine TranslationTranslation

Similar Papers 제목 키워드 기반

S$^{2}$-DMs:Skip-Step Diffusion Models

2024-01-03 · YiXuan Wang, Shuangyin Li

Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inheren…

Denoising Diffusion Implicit Models

2020-10-06 · ICLR 2021 1 · Jiaming Song, Chenlin Meng, Stefano Ermon

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate samp…

DenoisingImage Generation

Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs

2024-04-09 · Zander W. Blasingame, Chen Liu

Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a r…

Face Morphing Attack DetectionFace RecognitionGenerative Adversarial NetworkImage Morphing

Pseudo Numerical Methods for Diffusion Models on Manifolds

2022-02-20 · ICLR 2022 4 · Luping Liu, Yi Ren, Zhijie Lin, Zhou Zhao

Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce final samples. Several prior works…

DenoisingImage Generation

Iterative Neural Autoregressive Distribution Estimator NADE-k

2014-12-01 · NeurIPS 2014 12 · Tapani Raiko, Yao Li, Kyunghyun Cho, Yoshua Bengio

Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple s…

Density EstimationImage GenerationMissing ValuesVariational Inference