https://github.com/mohofar/beta-rank
공식 코드Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis
Papers with Code 아카이브
Network Pruning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 34
Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.
Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mts-ai/replaceme
공식 코드ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations
https://github.com/namhoonlee/snip-public
공식 코드SNIP: Single-shot Network Pruning based on Connection Sensitivity
https://github.com/namhoonlee/spp-public
공식 코드A Signal Propagation Perspective for Pruning Neural Networks at Initialization
https://github.com/nota-github/autobot_aaai23
공식 코드Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy
https://github.com/nvlabs/maskllm
공식 코드MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
https://github.com/ofsoundof/dhp
공식 코드https://github.com/oliviatessa/mothpruning
공식 코드Pruning deep neural networks generates a sparse, bio-inspired nonlinear controller for insect flight
https://github.com/osilly/kdfs
공식 코드Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
https://github.com/pralab/adversarialpruningbenchmark
공식 코드Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
https://github.com/qiaozhezhang/global-one-shot-pruning
공식 코드How Sparse Can We Prune A Deep Network: A Fundamental Limit Viewpoint
https://github.com/quackenbushlab/dash
공식 코드Pruning neural network models for gene regulatory dynamics using data and domain knowledge
https://github.com/racai-ai/romanian-distilbert
공식 코드Distilling the Knowledge of Romanian BERTs Using Multiple Teachers
https://github.com/rahimentezari/Sensys-ml2020
공식 코드https://github.com/rice-eic/spline-eb
공식 코드https://github.com/robbiemeyer/pw_loss_pruning
공식 코드https://github.com/roberttlange/es-lottery
공식 코드Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
https://github.com/rocktimjyotidas/gblm-pruner
공식 코드Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
https://github.com/rvdeo/bayes_prun
공식 코드https://github.com/saintslab/adver-fine
공식 코드https://github.com/schoonhovenrichard/LEAN_CNN_pruning
공식 코드LEAN: graph-based pruning for convolutional neural networks by extracting longest chains
https://github.com/sdc17/upop
공식 코드UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
https://github.com/seulkiyeom/LRP_Pruning_toy_example
공식 코드Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
https://github.com/shuvenduroy/unmixmatch
공식 코드Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data
https://github.com/shwai-he/sparseadapter
공식 코드SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters
https://github.com/siat-nlp/IPRLS
공식 코드Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification
https://github.com/siat-nlp/TPEM
공식 코드https://github.com/skyler120/sparsity-halo
공식 코드https://github.com/smn2010/fgc-pr
공식 코드Self-supervised Feature-Gate Coupling for Dynamic Network Pruning
https://github.com/snu-mllab/efficient-cnn-depth-compression
공식 코드Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
https://github.com/stephenqz/oats
공식 코드OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
https://github.com/szcompressor/DeepSZ
공식 코드DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression
https://github.com/taivu1998/ResNet-Regularization-Pruning
공식 코드How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference
https://github.com/terarachang/memdata
공식 코드Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
https://github.com/terarachang/mempi
공식 코드Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
https://github.com/theshineyue/hsr
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.