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/ejlb/squeezenet-chainer
공식 코드SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/ellisalicante/ma-fl-mia
공식 코드https://github.com/emannix/tintem-teacher-in-the-middle
공식 코드https://github.com/erfanhatefi/pruning-by-explaining-in-pytorch
공식 코드Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
https://github.com/erfanhatefi/sparc3
공식 코드Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
https://github.com/erilyth/HybridBinaryNetworks-WACV18
공식 코드Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory
https://github.com/facebookresearch/diffq
공식 코드Differentiable Model Compression via Pseudo Quantization Noise
https://github.com/fanhanwei/bocr
공식 코드Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning
https://github.com/fanxxxxyi/pic-pq
공식 코드Physics Inspired Criterion for Pruning-Quantization Joint Learning
https://github.com/fastmachinelearning/hls4ml
공식 코드https://github.com/fastmachinelearning/nac-opt
공식 코드https://github.com/fengfu-chris/caffe-twns
공식 코드https://github.com/flame-chasers/tbps-clip
공식 코드https://github.com/frankyu5666666/simpleunet
공식 코드Simple is what you need for efficient and accurate medical image segmentation
https://github.com/fraunhofer-scai/canonical-cnn
공식 코드https://github.com/fraunhoferhhi/DeepCABAC
공식 코드DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
https://github.com/fscdc/awesome-efficient-reasoning-models
공식 코드https://github.com/fzi-forschungszentrum-informatik/iterative-yolo-pruning
공식 코드Iterative Filter Pruning for Concatenation-based CNN Architectures
https://github.com/genezc/minidisc
공식 코드MiniDisc: Minimal Distillation Schedule for Language Model Compression
https://github.com/geondopark/ckd
공식 코드Distilling Linguistic Context for Language Model Compression
https://github.com/ghazaleh-mahmoodi/lxmert_compression
공식 코드https://github.com/gmkim-ai/promptkd
공식 코드PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
https://github.com/google-research/bert
공식 코드Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/google-research/google-research/tree/master/pruning_identified_exemplars
공식 코드https://github.com/grigorisg9gr/polynomials-for-augmenting-nns
공식 코드https://github.com/gsarridis/indistill
공식 코드InDistill: Information flow-preserving knowledge distillation for model compression
https://github.com/gsgoncalves/emnlp2023_llm_compression_and_social_bias
공식 코드Understanding the Effect of Model Compression on Social Bias in Large Language Models
https://github.com/guoyongcs/DRN
공식 코드Towards Lightweight Super-Resolution with Dual Regression Learning
https://github.com/guoyongcs/drc
공식 코드Towards Lightweight Super-Resolution with Dual Regression Learning
https://github.com/gyguo/pixeldistillation
공식 코드Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
https://github.com/gzyaftermath/cat-kd
공식 코드https://github.com/hahnyuan/llm-viewer
공식 코드https://github.com/haiv-lab/mekd
공식 코드Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
https://github.com/han678/correctednoisyei
공식 코드A Corrected Expected Improvement Acquisition Function Under Noisy Observations
https://github.com/hancheolp/compression_for_capturing_ambiguity
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.