Related papers: Instance-Free Domain Adaptive Object Detection
Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains a major challenge. Prevailing foundation models for TSAD predominantly rely on reconstruction-based…
Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…
Effective object detection in autonomous vehicles is challenged by deployment in diverse and unfamiliar environments. Online Source-Free Domain Adaptation (O-SFDA) offers model adaptation using a stream of unlabeled data from a target…
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…
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…
Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is…
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from such examples, various defense strategies have been…
Training an object instance detector where only a few training object images are available is a challenging task. One solution is a cut-and-paste method that generates a training dataset by cutting object areas out of training images and…
Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detection model trained…
Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, this such assumption may fail in different weather…
A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. Most existing methods adopt feature alignment either on the image level or instance level.…
Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e.g., with different styles. To address this problem, previous methods mainly use holistic…
Current Domain Adaptation (DA) methods based on deep architectures assume that the source samples arise from a single distribution. However, in practice, most datasets can be regarded as mixtures of multiple domains. In these cases…
Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new…
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…
We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a…
We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an…
Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deployment on resource-constrained edge devices. Object detection…
Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose…
Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…