Related papers: Consistency Regularisation for Unsupervised Domain…
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…
Semantic segmentation is a critical step in automated image interpretation and analysis where pixels are classified into one or more predefined semantically meaningful classes. Deep learning approaches for semantic segmentation rely on…
Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen…
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have…
Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural networks on resource-constrained hardware became possible with…
Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation)…
Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available. However, in many real-world scenarios, a small amount of labeled target data is available and…
Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric…
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider…
Supervised deep learning usually faces more challenges in medical images than in natural images. Since annotations in medical images require the expertise of doctors and are more time-consuming and expensive. Thus, some researchers turn to…
Contemporary domain adaptive semantic segmentation aims to address data annotation challenges by assuming that target domains are completely unannotated. However, annotating a few target samples is usually very manageable and worthwhile…
In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source…
Addressing performance degradation in 3D LiDAR semantic segmentation due to domain shifts (e.g., sensor type, geographical location) is crucial for autonomous systems, yet manual annotation of target data is prohibitive. This study…
Domain adaptation is especially important for robotics applications, where target domain training data is usually scarce and annotations are costly to obtain. We present a method for self-supervised domain adaptation for the scenario where…
Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground…
Domain transfer is a prevalent challenge in modern neural Information Retrieval (IR). To overcome this problem, previous research has utilized domain-specific manual annotations and synthetic data produced by consistency filtering to…
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution shifts from the target one. Mainstream UDA methods learn aligned features between…
Speckle noise has long been an extensively studied problem in medical imaging. In recent years, there have been significant advances in leveraging deep learning methods for noise reduction. Nevertheless, adaptation of supervised learning…
Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth…
Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions.…