Related papers: Exploring Object Relation in Mean Teacher for Cros…

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…

Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these…

Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised…

The scalability and complexity of deep learning models remains a key issue in many of visual recognition applications like, e.g., video surveillance, where fine tuning with labeled image data from each new camera is required to reduce the…

Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture…

Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains…

Domain adaptive object detection (DAOD) aims to improve the generalization ability of detectors when the training and test data are from different domains. Considering the significant domain gap, some typical methods, e.g., CycleGAN-based…

The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and…

Recently, an intriguing research trend for automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery has arisen: using simulated data to train ATR models is a feasible solution to the issue of inadequate measured data.…

Generic object detection has been immensely promoted by the development of deep convolutional neural networks in the past decade. However, in the domain shift circumstance, the changes in weather, illumination, etc., often cause domain gap,…

Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain…

3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor…

Most domain adaptation methods focus on single-source-single-target adaptation settings. Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains. To build a…

The lack of object-level annotations poses a significant challenge for object detection in remote sensing images (RSIs). To address this issue, active learning (AL) and semi-supervised learning (SSL) techniques have been proposed to enhance…

Despite growing interest in object detection, very few works address the extremely practical problem of cross-domain robustness especially for automative applications. In order to prevent drops in performance due to domain shift, we…

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this…

Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization. For example, a well-trained model on webface data cannot deal with the ID vs.…

Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…

Autonomous driving holds great promise in addressing traffic safety concerns by leveraging artificial intelligence and sensor technology. Multi-Object Tracking plays a critical role in ensuring safer and more efficient navigation through…

Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models…