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/facebookresearch/kill-the-bits
공식 코드And the Bit Goes Down: Revisiting the Quantization of Neural Networks
https://github.com/facebookresearch/qinco
공식 코드https://github.com/facebookresearch/secureflcompression
공식 코드Reconciling Security and Communication Efficiency in Federated Learning
https://github.com/facebookresearch/semi-discrete-flow
공식 코드Semi-Discrete Normalizing Flows through Differentiable Tessellation
https://github.com/facebookresearch/spreadingvectors
공식 코드https://github.com/facebookresearch/ternary_binary_transformer
공식 코드https://github.com/facebookresearch/vector_db_id_compression
공식 코드Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search
https://github.com/fanxxxxyi/pic-pq
공식 코드Physics Inspired Criterion for Pruning-Quantization Joint Learning
https://github.com/fartashf/nuqsgd
공식 코드NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization
https://github.com/fasterdecoding/teal
공식 코드https://github.com/fastmachinelearning/hls4ml
공식 코드https://github.com/fastmachinelearning/l1-jet-id
공식 코드https://github.com/fastmachinelearning/nac-opt
공식 코드https://github.com/fastmachinelearning/qonnx
공식 코드QONNX: Representing Arbitrary-Precision Quantized Neural Networks
https://github.com/fau-lms/bjontegaard
공식 코드The Bjøntegaard Bible -- Why your Way of Comparing Video Codecs May Be Wrong
https://github.com/fau-lms/vcm_scaling_lists
공식 코드https://github.com/fdbtrs/QuantFace
공식 코드QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization
https://github.com/fdu-me-arc/approxflow
공식 코드HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks
https://github.com/fdu-me-arc/heam
공식 코드HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks
https://github.com/fedespu/hvq
공식 코드Hierarchical Vector Quantization for Unsupervised Action Segmentation
https://github.com/felix-st/fairglvq
공식 코드https://github.com/fenghz/baffle
공식 코드BAFFLE: A Baseline of Backpropagation-Free Federated Learning
https://github.com/fjxmlzn/summary_statistic_privacy
공식 코드https://github.com/flanders-make-vzw/hpc2edge
공식 코드Optimizing edge AI models on HPC systems with the edge in the loop
https://github.com/fmi-basel/binary-activation-maps-sqp
공식 코드https://github.com/fostiropoulos/depthwise-quantization
공식 코드https://github.com/foundationvision/unitok
공식 코드UniTok: A Unified Tokenizer for Visual Generation and Understanding
https://github.com/fpgasystems/MLWeaving
공식 코드https://github.com/frankzheng2022/prise
공식 코드PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
https://github.com/frapez1/SQ-GAN
공식 코드SQ-GAN: Semantic Image Communications Using Masked Vector Quantization
https://github.com/fraunhoferhhi/DeepCABAC
공식 코드DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
https://github.com/fraunhoferhhi/Self-Organizing-Gaussians
공식 코드Compact 3D Scene Representation via Self-Organizing Gaussian Grids
https://github.com/freddyAdjh/Federated-security
공식 코드Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model
https://github.com/fudan-generative-vision/hallo2
공식 코드Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
https://github.com/funaudiollm/cosyvoice
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.