51 citations · 190 across the 18 of their papers we have counts for
18 papers
Multi-modal Domain Adaptation for REG via Relation Transfer
Yifan Ding, Liqiang Wang, Boqing Gong
Domain adaptation, which aims to transfer knowledge between domains, has been well studied in many areas such as image classification and object detection. However, for multi-modal…
FF-LINS: A Consistent Frame-to-Frame Solid-State-LiDAR-Inertial State Estimator
Hailiang Tang, Tisheng Zhang, Xiaoji Niu +3
Most of the existing LiDAR-inertial navigation systems are based on frame-to-map registrations, leading to inconsistency in state estimation. The newest solid-state LiDAR with a no…
PO-VINS: An Efficient and Robust Pose-Only Visual-Inertial State Estimator With LiDAR Enhancement
Hailiang Tang, Tisheng Zhang, Liqiang Wang +2
The pose adjustment (PA) with a pose-only visual representation has been proven equivalent to the bundle adjustment (BA), while significantly improving the computational efficiency…
On Calibrating Semantic Segmentation Models: Analyses and An Algorithm
Dongdong Wang, Boqing Gong, Liqiang Wang
We study the problem of semantic segmentation calibration. Lots of solutions have been proposed to approach model miscalibration of confidence in image classification. However, to…
Ranking Neural Checkpoints
Yandong Li, Xuhui Jia, Ruoxin Sang +4
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DN…
Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization
Li Ren, Kai Li, LiQiang Wang +1
Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to…
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
Dongdong Wang, Yandong Li, Liqiang Wang +1
We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this proble…
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang +2
Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our e…
Depthwise Convolution is All You Need for Learning Multiple Visual Domains
Yunhui Guo, Yandong Li, Rogerio Feris +2
There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can…
Learning to Adaptively Scale Recurrent Neural Networks
Hao Hu, Liqiang Wang, Guo-Jun Qi
Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time ser…
Asynchronous Delay-Aware Accelerated Proximal Coordinate Descent for Nonconvex Nonsmooth Problems
Ehsan Kazemi, Liqiang Wang
Nonconvex and nonsmooth problems have recently attracted considerable attention in machine learning. However, developing efficient methods for the nonconvex and nonsmooth optimizat…
AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
Liheng Zhang, Guo-Jun Qi, Liqiang Wang +1
The success of deep neural networks often relies on a large amount of labeled examples, which can be difficult to obtain in many real scenarios. To address this challenge, unsuperv…
A Proximal Zeroth-Order Algorithm for Nonconvex Nonsmooth Problems
Ehsan Kazemi, Liqiang Wang
In this paper, we focus on solving an important class of nonconvex optimization problems which includes many problems for example signal processing over a networked multi-agent sys…
How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization
Yandong Li, Liqiang Wang, Tianbao Yang +1
The large volume of video content and high viewing frequency demand automatic video summarization algorithms, of which a key property is the capability of modeling diversity. If vi…
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
Yifan Ding, Liqiang Wang, Deliang Fan +1
The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dat…
Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
Xiang Wei, Boqing Gong, Zixia Liu +2
Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train. This issue is formally analyzed by \cit…
An Intelligent QoS Identification for Untrustworthy Web Services Via Two-phase Neural Networks
Weidong Wang, Liqiang Wang, Wei Lu
QoS identification for untrustworthy Web services is critical in QoS management in the service computing since the performance of untrustworthy Web services may result in QoS downg…
HBTM: A Heartbeat-based Behavior Detection Mechanism for POSIX Threads and OpenMP Applications
Weidong Wang, Chunhua Liao, Liqiang Wang +2
Extreme-scale computing involves hundreds of millions of threads with multi-level parallelism running on large-scale hierarchical and heterogeneous hardware. In POSIX threads and O…