Recent advances on image edge detection: A comprehensive review

J Jing, S Liu, G Wang, W Zhang, C Sun - Neurocomputing, 2022 - Elsevier
Edge detection is one of the most important and fundamental problems in the field of
computer vision and image processing. Edge contours extracted from images are widely …

Camouflaged object detection

DP Fan, GP Ji, G Sun, MM Cheng… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present a comprehensive study on a new task named camouflaged object detection
(COD), which aims to identify objects that are" seamlessly" embedded in their surroundings …

Leveraging instance-, image-and dataset-level information for weakly supervised instance segmentation

Y Liu, YH Wu, P Wen, Y Shi, Y Qiu… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Weakly supervised semantic instance segmentation with only image-level supervision,
instead of relying on expensive pixel-wise masks or bounding box annotations, is an …

Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network

M Zhu, P Pan, W Chen, Y Yang - Proceedings of the AAAI conference on …, 2020 - aaai.org
This work focuses on the extremely low-light image enhancement, which aims to improve
image brightness and reveal hidden information in darken areas. Recently, image …

Miniseg: An extremely minimum network for efficient covid-19 segmentation

Y Qiu, Y Liu, S Li, J Xu - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
The rapid spread of the new pandemic, ie, COVID-19, has severely threatened global
health. Deep-learning-based computer-aided screening, eg, COVID-19 infected CT area …

Lightweight salient object detection via hierarchical visual perception learning

Y Liu, YC Gu, XY Zhang, W Wang… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Recently, salient object detection (SOD) has witnessed vast progress with the rapid
development of convolutional neural networks (CNNs). However, the improvement of SOD …

Open-world instance segmentation: Exploiting pseudo ground truth from learned pairwise affinity

W Wang, M Feiszli, H Wang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Open-world instance segmentation is the task of grouping pixels into object instances
without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely …

[PDF][PDF] Transformer in convolutional neural networks

Y Liu, G Sun, Y Qiu, L Zhang… - arXiv preprint arXiv …, 2021 - homes.esat.kuleuven.be
We tackle the low-efficiency flaw of vision transformer caused by the high
computational/space complexity in Multi-Head Self-Attention (MHSA). To this end, we …

Rethinking computer-aided tuberculosis diagnosis

Y Liu, YH Wu, Y Ban, H Wang… - Proceedings of the …, 2020 - openaccess.thecvf.com
As a serious infectious disease, tuberculosis (TB) is one of the major threats to human health
worldwide, leading to millions of death every year. Although early diagnosis and treatment …

Multi-scale interaction for real-time lidar data segmentation on an embedded platform

S Li, X Chen, Y Liu, D Dai… - IEEE Robotics and …, 2021 - ieeexplore.ieee.org
Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles
and robots, which are usually equipped with an embedded platform and have limited …