DUCKQUANT / THE QUANT & AI DIRECTORY
1,058 resources, ranked by in-directory PageRank
Publication: Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs. Published Jan 31, 2024.
Publication: Data-Free Quantization via Pseudo-label Filtering. Published 2024.
Electronic proceedings of IJCAI 2024
Publication: Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. Published Nov 29, 2021.
GACT: Activation Compressed Training for Generic Network ArchitecturesXiaoxuan Liu, Lianmin Zheng, Dequan Wang, Yukuo Cen, Weize Chen,&nb...
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksRunpei Dong, Zhanhong Tan, Mengdi Wu, Linfeng Zhang, Kaisheng Ma...
SDQ: Stochastic Differentiable Quantization with Mixed PrecisionXijie Huang, Zhiqiang Shen, Shichao Li, Zechun Liu, Hu Xianghong, Je...
Publication: Distribution-sensitive Information Retention for Accurate Binary Neural Network. Published Sep 25, 2021.
Publication: Genie: Show Me the Data for Quantization. Published Dec 9, 2022.
Publication: Adaptive Data-Free Quantization. Published Mar 13, 2023.
Publication: Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection. Published Jun 12, 2023.
HAWQ-V3: Dyadic Neural Network QuantizationZhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wa...
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed TrainingJianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, I...
Accurate Post Training Quantization With Small Calibration SetsItay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, Daniel SoudryLately, p...
Electronic proceedings of IJCAI 2022
Electronic proceedings of IJCAI 2022
Publication: Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance. Published Mar 16, 2022.
Publication: Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks. Published Sep 30, 2020.
Publication: Network Quantization with Element-wise Gradient Scaling. Published Apr 2, 2021.
Publication: Zero-shot Adversarial Quantization. Published Mar 29, 2021.
Publication: Learnable Companding Quantization for Accurate Low-bit Neural Networks. Published Mar 12, 2021.
Publication: Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks. Published Oct 29, 2020.
Publication: Diversifying Sample Generation for Accurate Data-Free Quantization. Published Mar 1, 2021.
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and AcceleratorsYonggan Fu, Yongan Zhang, Yang Zhang, Da...
Differentiable Dynamic Quantization with Mixed Precision and Adaptive ResolutionZhaoyang Zhang, Wenqi Shao, Jinwei Gu, Xiaogang Wang, Pin...
Explore this resource at its source website for documentation and current information.
Publication: BiDet: An Efficient Binarized Object Detector. Published Mar 9, 2020.
Publication: AQD: Towards Accurate Fully-Quantized Object Detection. Published Jul 14, 2020.
Publication: Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric. Published Apr 19, 2023.
Publication: PACT: Parameterized Clipping Activation for Quantized Neural Networks. Published May 16, 2018.
Publication: Data-Free Quantization Through Weight Equalization and Bias Correction. Published 2019.
Publication: Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision. Published Feb 20, 2020.
Publication: Scalable Verification of Quantized Neural Networks (Technical Report). Published Dec 15, 2020.
