Anton Trusov

Часть публикаций из профиля, по году от новых к старым. Это не полный список последних работ автора; работы без года — в конце.

• Fast- and memory-efficient convolution on ARM for computer vision neural networks2026
• Fast and accurate RFD-like descriptor approximation for SIMD architectures2025
• 4.6-Bit Quantization for Fast and Accurate Neural Network Inference on CPUs2024
• FARA: fast and accurate RFDoc descriptor approximation2024
• Training of binary neural network models using continuous approximation2024
• Neuron-by-Neuron Quantization for Efficient Low-Bit QNN Training2023 · аннотациясвернуть

  Quantized neural networks (QNNs) are widely used to achieve computationally efficient solutions to recognition problems. Overall, eight-bit QNNs have almost the same accuracy as full-precision networks, but working…

• Fast Computation of RFD-Like Descriptors in Four Orientations2023
• PESAC, the Generalized Framework for RANSAC-Based Methods on SIMD Computing Platforms2023