Related papers: ReSimAD: Zero-Shot 3D Domain Transfer for Autonomo…
Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…
Manual annotation of 3D medical images for segmentation tasks is tedious and time-consuming. Moreover, data privacy limits the applicability of crowd sourcing to perform data annotation in medical domains. As a result, training deep neural…
Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a…
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but…
Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…
Object detection models trained on a source domain often exhibit significant performance degradation when deployed in unseen target domains, due to various kinds of variations, such as sensing conditions, environments and data…
Transfer learning is an important field of machine learning in general, and particularly in the context of fully autonomous driving, which needs to be solved simultaneously for many different domains, such as changing weather conditions and…
Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or…
Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during…
In the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes serve as the critical bridge connecting low-level geometric sensing with high-level semantic understanding. We present DINO\_4D, introducing…
Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…
Transferring skills between different objects remains one of the core challenges of open-world robot manipulation. Generalization needs to take into account the high-level structural differences between distinct objects while still…
We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different,…
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain. However, current UDA methods typically assume a shared label space…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…
Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would…
Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that…
Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains…
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain…