Related papers: RPCL: A Framework for Improving Cross-Domain Detec…

Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…

Object detection models trained on a source domain often exhibit significant performance degradation when deployed in unseen target domains, due to various kinds of variations, such as sensing conditions, environments and data…

Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision…

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…

Domain adaptation for Cross-LiDAR 3D detection is challenging due to the large gap on the raw data representation with disparate point densities and point arrangements. By exploring domain-invariant 3D geometric characteristics and motion…

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

Object detectors are usually trained with large amount of labeled data, which is expensive and labor-intensive. Pre-trained detectors applied to unlabeled dataset always suffer from the difference of dataset distribution, also called domain…

Over the last years, dictionary learning method has been extensively applied to deal with various computer vision recognition applications, and produced state-of-the-art results. However, when the data instances of a target domain have a…

In addressing the persistent challenges of data-sparsity and cold-start issues in domain-expert recommender systems, Cross-Domain Recommendation (CDR) emerges as a promising methodology. CDR aims at enhancing prediction performance in the…

Change detection encompasses a variety of task types, and the goal of building change detection (BCD) tasks is to accurately locate buildings and distinguish changed building areas. In recent years, various deep learning-based BCD methods…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA.…

While existing semi-supervised object detection (SSOD) methods perform well in general scenes, they encounter challenges in handling oriented objects in aerial images. We experimentally find three gaps between general and oriented object…

Multi-task learning based video anomaly detection methods combine multiple proxy tasks in different branches to detect video anomalies in different situations. Most existing methods either do not combine complementary tasks to effectively…

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the…

Unsupervised domain adaptive object detection aims to learn a robust detector in the domain shift circumstance, where the training (source) domain is label-rich with bounding box annotations, while the testing (target) domain is…

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches…

Audio-Visual Source Localization (AVSL) is the task of identifying specific sounding objects in the scene given audio cues. In our work, we focus on semi-supervised AVSL with pseudo-labeling. To address the issues with vanilla hard…

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through…