-
Article
Open AccessUnsupervised Point Cloud Representation Learning by Clustering and Neural Rendering
Data augmentation has contributed to the rapid advancement of unsupervised learning on 3D point clouds. However, we argue that data augmentation is not ideal, as it requires a careful application-dependent sel...
-
Article
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to poor generalization ability, which limits real-wo...
-
Article
Nonlinear neurons with human-like apical dendrite activations
In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer. Inspired by some recent discoveries in neuro...
-
Article
HiEve: A Large-Scale Benchmark for Human-Centric Video Analysis in Complex Events
Along with the development of modern smart cities, human-centric video analysis has been encountering the challenge of analyzing diverse and complex events in real scenes. A complex event relates to dense crow...
-
Article
Self-training transformer for source-free domain adaptation
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation. Previous works on SFDA mainly focus on aligning the cross-domain dist...
-
Article
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis
We present a novel bipartite graph reasoning Generative Adversarial Network (BiGraphGAN) for two challenging tasks: person pose and facial image synthesis. The proposed graph generator consists of two novel bl...
-
Chapter and Conference Paper
Budget-Aware Pruning for Multi-domain Learning
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such r...
-
Article
Curriculum Learning: A Survey
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on rando...
-
Article
Deep traffic sign detection and recognition without target domain real images
Deep learning has become a standard approach to machine vision in recent years. Despite several advances, it requires large amounts of annotated data. Nonetheless, in many applications, large-scale data acquis...
-
Chapter and Conference Paper
Class-Incremental Novel Class Discovery
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has b...
-
Chapter and Conference Paper
GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This...
-
Chapter and Conference Paper
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data. The large domai...
-
Chapter and Conference Paper
Uncertainty-Guided Source-Free Domain Adaptation
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data and the domain shift makes the...
-
Chapter and Conference Paper
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities. In this paper, we systematic...
-
Chapter and Conference Paper
CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for d...
-
Chapter and Conference Paper
Batch-Efficient EigenDecomposition for Small and Medium Matrices
EigenDecomposition (ED) is at the heart of many computer vision algorithms and applications. One crucial bottleneck limiting its usage is the expensive computation cost, particularly for a mini-batch of matric...
-
Chapter and Conference Paper
3D-Aware Semantic-Guided Generative Model for Human Synthesis
Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid/semi-rigid objects, such as hu...
-
Article
Viewpoint and Scale Consistency Reinforcement for UAV Vehicle Re-Identification
This paper studies vehicle ReID in aerial videos taken by Unmanned Aerial Vehicles (UAVs). Compared with existing vehicle ReID tasks performed with fixed surveillance cameras, UAV vehicle ReID is still under-e...
-
Article
Open AccessTriGAN: image-to-image translation for multi-source domain adaptation
Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources...
-
Article
Special Issue on Generating Realistic Visual Data of Human Behavior
