Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 10
- 보존된 평가 기록
- 32
Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).
Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zju-jiangqi/qdmr
공식 코드https://github.com/zjuchenwei/vector-line-quantization
공식 코드Vector and Line Quantization for Billion-scale Similarity Search on GPUs
https://github.com/zkkli/i-vit
공식 코드I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
https://github.com/zkkli/psaq-vit
공식 코드Patch Similarity Aware 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://github.com/znlp/zero-shot-st
공식 코드Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
https://github.com/zpbao/discovery_obj_move
공식 코드https://github.com/zpbao/motok
공식 코드https://github.com/zqu1992/ALQ
공식 코드https://github.com/zysxmu/ddtb
공식 코드Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
https://github.com/zysxmu/dfsq
공식 코드Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
https://github.com/zysxmu/fdda
공식 코드Fine-grained Data Distribution Alignment for Post-Training Quantization
https://github.com/zysxmu/ias-vit
공식 코드I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
https://github.com/zysxmu/intraq
공식 코드IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
https://github.com/zysxmu/lts
공식 코드Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
https://github.com/zysxmu/mbquant
공식 코드MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
https://github.com/zysxmu/multiquant
공식 코드MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
https://github.com/zzh-tech/animation-from-blur
공식 코드Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
https://github.com/zzs1994/CVQN
공식 코드Channel-Level Variable Quantization Network for Deep Image Compression
https://github.com/zzwjames/failurellmunlearning
공식 코드https://github.com/zzzqt/dm4u1
공식 코드Physics-Conditioned Diffusion Models for Lattice Gauge Theory
https://gitlab.com/Queuecumber/quantization-guided-ac
공식 코드https://gitlab.com/aiCTX/synoploss
공식 코드Optimizing the energy consumption of spiking neural networks for neuromorphic applications
https://gitlab.com/esrgv3/q7-capsnets
공식 코드https://gitlab.com/esrgv3/qnn-adversarial-robustness
공식 코드David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edge
https://gitlab.com/ones-ai/eval-quant-llms
공식 코드https://gitlab.com/ones-ai/mixed-non-linear-quantization
공식 코드https://gitlab.com/ones-ai/q-hyvit
공식 코드https://gitlab.com/synsense/synoploss
공식 코드Optimizing the energy consumption of spiking neural networks for neuromorphic applications
https://gitlab.com/viper-purdue/fmpq
공식 코드Flexible Mixed Precision Quantization for Learned Image Compression
https://gitlab.com/viper-purdue/lic-pruning
공식 코드Structured Pruning and Quantization for Learned Image Compression
https://gitlab.com/viper-purdue/qarv-release
공식 코드QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
https://zenodo.org/record/7981159
공식 코드A Transfer Learning and Explainable Solution to Detect mpox from Smartphones images
https://gitee.com/HarveyYeung/PUGAN_MindSpore.git
PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators
https://github.com/0jason000/Adabin
AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.