Related papers: What, How, and When Should Object Detectors Update…

Data distribution shift is a common problem in machine learning-powered smart city applications where the test data differs from the training data. Augmenting smart city applications with online machine learning models can handle this issue…

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…

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt…

This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Online test-time adaptation aims to dynamically adjust a network model in real-time based on sequential input samples during the inference stage. In this work, we find that, when applying a transformer network model to a new target domain,…

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Continual Test-Time Adaptation (CTTA) task investigates effective domain adaptation under the scenario of continuous domain shifts during testing time. Due to the utilization of solely unlabeled samples, there exists significant uncertainty…

We address the task of domain adaptation in object detection, where there is a domain gap between a domain with annotations (source) and a domain of interest without annotations (target). As an effective semi-supervised learning method, the…

Given labeled instances on a source domain and unlabeled ones on a target domain, unsupervised domain adaptation aims to learn a task classifier that can well classify target instances. Recent advances rely on domain-adversarial training of…

Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely ignore the instantaneous data distribution during model…

Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple…

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…

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta…

Fully test-time adaptation aims to adapt a network model online based on sequential analysis of input samples during the inference stage. We observe that, when applying a transformer network model into a new domain, the self-attention…

DETR-style detectors stand out amongst in-domain scenarios, but their properties in domain shift settings are under-explored. This paper aims to build a simple but effective baseline with a DETR-style detector on domain shift settings based…

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least…

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…

Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in performance, they typically perform category-agnostic domain…