Related papers: Prompt-Driven Temporal Domain Adaptation for Night…
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated.…
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets.…
Domain adaptation (DA) strives to mitigate the domain gap between the source domain where a model is trained, and the target domain where the model is deployed. When a deep learning model is deployed on an aerial platform, it may face…
Machine learning traditionally assumes that the training and testing data are distributed independently and identically. However, in many real-world settings, the data distribution can shift over time, leading to poor generalization of…
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons. Since covering all domains with annotated…
Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of…
This paper investigates the problem of traffic surveillance using an unmanned aerial vehicle (UAV) and proposes a domain-knowledge-aided airborne ground moving targets tracking algorithm. To improve the accuracy of multiple targets…
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…
Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…
Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been…
Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In…
Due to changes in model dynamics or unexpected disturbances, an autonomous robotic system may experience unforeseen challenges during real-world operations which may affect its safety and intended behavior: in particular actuator and system…
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a…
Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically…
Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…
Low-altitude Unmanned Aerial Vehicle (UAV) networks rely on robust semantic segmentation as a foundational enabler for distributed sensing-communication-control co-design across heterogeneous agents within the network. However, segmentation…
Due to the lack of large-scale labeled Thermal InfraRed (TIR) training datasets, most existing TIR trackers are trained directly on RGB datasets. However, tracking methods trained on RGB datasets suffer a significant drop-off in TIR data…
Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to…
Most previous progress in object tracking is realized in daytime scenes with favorable illumination. State-of-the-arts can hardly carry on their superiority at night so far, thereby considerably blocking the broadening of visual…
Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this task, numerous…