26 citations · 135 across the 22 of their papers we have counts for
10 papers · 1 filter
Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
Jiachen Li, Bowen Cheng, Rogerio Feris +4
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based…
Interpretable Visual Reasoning via Induced Symbolic Space
Zhonghao Wang, Kai Wang, Mo Yu +4
We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; an…
Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation
Zhonghao Wang, Yunchao Wei, Rogerior Feris +4
Learning segmentation from synthetic data and adapting to real data can significantly relieve human efforts in labelling pixel-level masks. A key challenge of this task is how to a…
Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
Zhonghao Wang, Mo Yu, Yunchao Wei +5
We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (rea…
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
Xiaofan Zhang, Haoming Lu, Cong Hao +9
Object detection and tracking are challenging tasks for resource-constrained embedded systems. While these tasks are among the most compute-intensive tasks from the artificial inte…
SPGNet: Semantic Prediction Guidance for Scene Parsing
Bowen Cheng, Liang-Chieh Chen, Yunchao Wei +6
Multi-scale context module and single-stage encoder-decoder structure are commonly employed for semantic segmentation. The multi-scale context module refers to the operations to ag…