72 citations · 80 across the 7 of their papers we have counts for
4 papers · 1 filter
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…
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…