Papers with Code 아카이브
Model Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 14
Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/LMA-NeurIPS19/LMA
공식 코드https://github.com/MAC-AutoML/YOCO-BERT
공식 코드https://github.com/NVlabs/Sana
공식 코드https://github.com/NVlabs/condensa
공식 코드https://github.com/NervanaSystems/distiller
공식 코드Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
https://github.com/NiuTrans/NiuTrans.NMT
공식 코드https://github.com/OmarErak/CsiNet_Optimized
공식 코드Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback
https://github.com/PKUnlp-icler/ContrastivePruning
공식 코드From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression
https://github.com/ParkLabML/Dirichlet_Pruning
공식 코드https://github.com/PengchaoHan/RDSKD
공식 코드Robustness and Diversity Seeking Data-Free Knowledge Distillation
https://github.com/PerforatedAI/PerforatedAI-API
공식 코드Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks
https://github.com/PratikGarai/Semantic-Segmentation-UNet-Federated
공식 코드https://github.com/QingyuanWang/dyce
공식 코드DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling
https://github.com/QingyuanWang/tinysaver
공식 코드https://github.com/RUCAIBox/MPOP
공식 코드https://github.com/RobustBench/robustbench
공식 코드A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness
https://github.com/RuishanLiu/GAN-TSC
공식 코드Teacher-Student Compression with Generative Adversarial Networks
https://github.com/RunpeiDong/DGMS
공식 코드Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
https://github.com/SCUT-AILab/DCP
공식 코드Discrimination-aware Channel Pruning for Deep Neural Networks
https://github.com/SeongKu-Kang/DE-RRD_CIKM20
공식 코드DE-RRD: A Knowledge Distillation Framework for Recommender System
https://github.com/SforAiDl/KD_Lib
공식 코드KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
https://github.com/ShaowuChen/JointSVD
공식 코드Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
https://github.com/ShaowuChen/WHC
공식 코드WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks
https://github.com/SkoltechAI/fewbit
공식 코드Memory-Efficient Backpropagation through Large Linear Layers
https://github.com/TAU-MLwell/Rubust-Model-Compression
공식 코드https://github.com/Tangshitao/Semi-supervised-Adaptive-Distillation
공식 코드Learning Efficient Detector with Semi-supervised Adaptive Distillation
https://github.com/UCMerced-ML/LC-model-compression
공식 코드https://github.com/UMBCvision/CompReSS
공식 코드CompRess: Self-Supervised Learning by Compressing Representations
https://github.com/UoS-EEC/DynamicOFA
공식 코드Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices
https://github.com/VITA-Group/EarlyBERT
공식 코드EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
https://github.com/VainF/Data-Free-Adversarial-Distillation
공식 코드https://github.com/VainF/Torch-Pruning
공식 코드https://github.com/WonbinKweon/BD_WWW2021
공식 코드https://github.com/Xming-Z/RobustKD
공식 코드Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model
https://github.com/ZJULearning/COP
공식 코드COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.