72 citations · 80 across the 7 of their papers we have counts for
7 papers
Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers
Rui Ding, Liang Yong, Sihuan Zhao +4
Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, th…
STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks
Haoran Gao, Xichuan Zhou, Yingcheng Lin +3
The prevailing of artificial intelligence-of-things calls for higher energy-efficient edge computing paradigms, such as neuromorphic agents leveraging brain-inspired spiking neural…
EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution
Xi Su, Xiangfei Shen, Mingyang Wan +4
Single hyperspectral image super-resolution (single-HSI-SR) aims to improve the resolution of a single input low-resolution HSI. Due to the bottleneck of data scarcity, the develop…
BiGSeT: Binary Mask-Guided Separation Training for DNN-based Hyperspectral Anomaly Detection
Haijun Liu, Xi Su, Xiangfei Shen +2
Hyperspectral anomaly detection (HAD) aims to recognize a minority of anomalies that are spectrally different from their surrounding background without prior knowledge. Deep neural…
Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification
Haijun Liu, Yanxia Chai, Xiaoheng Tan +2
In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). In general, ReID models are alw…
MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time
Xichuan Zhou, Yicong Peng, Chunqiao Long +2
Monocular multi-object detection and localization in 3D space has been proven to be a challenging task. The MoNet3D algorithm is a novel and effective framework that can predict th…
Neural Network Activation Quantization with Bitwise Information Bottlenecks
Xichuan Zhou, Kui Liu, Cong Shi +2
Recent researches on information bottleneck shed new light on the continuous attempts to open the black box of neural signal encoding. Inspired by the problem of lossy signal compr…