Related papers: Unsupervised Adversarial Visual Level Domain Adapt…

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

Urban material recognition in remote sensing imagery is a highly relevant, yet extremely challenging problem due to the difficulty of obtaining human annotations, especially on low resolution satellite images. To this end, we propose an…

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy…

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…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In…

Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…

We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on…

The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to…

Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access…

Virtual Adversarial Training has recently seen a lot of success in semi-supervised learning, as well as unsupervised Domain Adaptation. However, so far it has been used on input samples in the pixel space, whereas we propose to apply it…

Open World Object Detection (OWOD) combines open-set object detection with incremental learning capabilities to handle the challenge of the open and dynamic visual world. Existing works assume that a foreground predictor trained on the seen…

Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial…

We propose an end-to-end learning framework for segmenting generic objects in both images and videos. Given a novel image or video, our approach produces a pixel-level mask for all "object-like" regions---even for object categories never…

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first…

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an…

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…