https://github.com/yuchaoli/KSE
공식 코드Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
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/yueb17/pemn
공식 코드https://github.com/yuhao318/UP-ViT
공식 코드https://github.com/yuhuixu1993/SLQ
공식 코드Deep Neural Network Compression with Single and Multiple Level Quantization
https://github.com/yulongtzzz/Stealthy-Backdoors-as-Compression-Artifacts
공식 코드https://github.com/yushansu/prumux
공식 코드https://github.com/yusx-swapp/gnn-rl-model-compression
공식 코드Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
https://github.com/yuxwind/ExactCompression
공식 코드Scaling Up Exact Neural Network Compression by ReLU Stability
https://github.com/zeyneddinoz/subMFL
공식 코드subMFL: Compatiple subModel Generation for Federated Learning in Device Heterogenous Environment
https://github.com/zeyuanyin/LTH-Backdoor
공식 코드Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis
https://github.com/zhang-fengdi/ControlGS
공식 코드Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian Splatting
https://github.com/zhen-dong/hawq
공식 코드https://github.com/zhichaoxu-shufe/beyond-perplexity-compression-safety-eval
공식 코드Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression
https://github.com/zhou-hangyu/randes
공식 코드RanDeS: Randomized Delta Superposition for Multi-Model Compression
https://github.com/zhuang-group/saq
공식 코드https://github.com/zihao-wang/sparsity-by-redundancy
공식 코드https://github.com/zihao-wang/spred
공식 코드https://github.com/zip-group/saq
공식 코드https://github.com/ziplab/saq
공식 코드https://github.com/zipnn/zipnn
공식 코드https://github.com/ziweiwangthu/seernet
공식 코드Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
https://github.com/zj-binxia/bbcu
공식 코드Basic Binary Convolution Unit for Binarized Image Restoration Network
https://github.com/zjersey/lightseq-arm
공식 코드https://github.com/zju-swj/kt
공식 코드https://github.com/zju-swj/rld
공식 코드https://github.com/zju-vipa/NetGraft
공식 코드Progressive Network Grafting for Few-Shot Knowledge Distillation
https://github.com/zkkli/psaq-vit
공식 코드PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
https://github.com/zkkli/repq-vit
공식 코드RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
https://gitlab.com/dxxz/Self-Supervised-GAN-Compression-Appendix
공식 코드https://gitlab.com/viper-purdue/lic-pruning
공식 코드Structured Pruning and Quantization for Learned Image Compression
https://github.com/2023-MindSpore-1/ms-code-214/tree/main/I3D
I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
https://github.com/2023-MindSpore-1/ms-code-217/tree/main/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/2023-MindSpore-4/Code11/tree/main/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/2023-MindSpore-4/Code8/tree/main/advanced_east
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
https://github.com/Adlik/model_optimizer
https://github.com/AhmadQasim/proxylessnas-dense
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.