PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Posts by Tag
-
Structured Pruning
Movement Pruning
BERT
Model Compression
Uniform Quantization
Low-rank Approximation
LRA
SVD
ResNet-18
Vision Transformer
Light-weighted CNN
ImageNet
Apple
Mohammad Rastegari
Mobile ViT
On-device AI
Image Classification
Object Detection
Efficient Architecture
CNN
Language Model
Pruning
Knowledge Distillation
Transfer Learning
Quantization
Once for all
Efficient Transformer
//
-
Unstructured
Speech
Recognition
Model
Compression
Magnitude-based
Wav2vec_2
-
//
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Apple
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
BERT
Understanding and Overcoming the Challenges of Efficient Transformer Quantization
Link : https://arxiv.org/abs/2109.12948v1
Block Pruning For Faster Transformers
Link : https://arxiv.org/abs/2109.04838
CNN
Non-deep Networks
Link : https://arxiv.org/abs/2110.07641
Compression
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Efficient Architecture
Non-deep Networks
Link : https://arxiv.org/abs/2110.07641
Efficient Transformer
Sparse is Enough in Scaling Transformers
Link : https://arxiv.org/pdf/2111.12763.pdf 저자/학회 특이사항 Google Research in Europe, Reformer 저자도 있고 (Łukasz Kaiser), Performer 저자도 있고(Afroz Mohiu...
Image Classification
Non-deep Networks
Link : https://arxiv.org/abs/2110.07641
ImageNet
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Knowledge Distillation
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
LRA
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Link: https://arxiv.org/pdf/2107.11442.pdf
Language Model
Sparse is Enough in Scaling Transformers
Link : https://arxiv.org/pdf/2111.12763.pdf 저자/학회 특이사항 Google Research in Europe, Reformer 저자도 있고 (Łukasz Kaiser), Performer 저자도 있고(Afroz Mohiu...
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Light-weighted CNN
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Low-rank Approximation
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Link: https://arxiv.org/pdf/2107.11442.pdf
Magnitude-based
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Mobile ViT
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Model
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Model Compression
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Link: https://arxiv.org/pdf/2107.11442.pdf
Understanding and Overcoming the Challenges of Efficient Transformer Quantization
Link : https://arxiv.org/abs/2109.12948v1
Block Pruning For Faster Transformers
Link : https://arxiv.org/abs/2109.04838
Mohammad Rastegari
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Movement Pruning
Block Pruning For Faster Transformers
Link : https://arxiv.org/abs/2109.04838
Object Detection
Non-deep Networks
Link : https://arxiv.org/abs/2110.07641
On-device AI
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Once for all
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Pruning
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Quantization
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Recognition
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
ResNet-18
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Link: https://arxiv.org/pdf/2107.11442.pdf
SVD
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Link: https://arxiv.org/pdf/2107.11442.pdf
Speech
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Structured Pruning
Block Pruning For Faster Transformers
Link : https://arxiv.org/abs/2109.04838
Transfer Learning
Prune Once for All: Sparse Pre-Trained Language Models
Link : https://arxiv.org/pdf/2111.05754.pdf 저자/학회 특이사항 Intel Labs, Israel ENLSP NeurIPS Workshop 2021 제안하는 방법에 대해서는 의구심이 조금 생기지...
Uniform Quantization
Understanding and Overcoming the Challenges of Efficient Transformer Quantization
Link : https://arxiv.org/abs/2109.12948v1
Unstructured
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...
Vision Transformer
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Link : https://arxiv.org/abs/2110.02178?context=cs.LG
Wav2vec_2
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitiont
Link : https://openreview.net/pdf?id=UoVpP8R2Vn 저자/학회 특이사항 Neurips 2021 Spotlight paper 주저자는 MIT CSAIL PARP unstructured mag...