Related papers: A Fully Convolutional Tri-branch Network (FCTN) fo…
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe…
In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation. Central to our approach is the innovative Multi-scale Text-aware ViT-CNN Fusion scheme. This scheme adeptly combines the…
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object…
Computer vision systems currently lack the ability to reliably recognize artistically rendered objects, especially when such data is limited. In this paper, we propose a method for recognizing objects in artistic modalities (such as…
Domain Adaptation is a technique to address the lack of massive amounts of labeled data in unseen environments. Unsupervised domain adaptation is proposed to adapt a model to new modalities using solely labeled source data and unlabeled…
In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more,…
Unsupervised Domain Adaptation (UDA) aims to solve the problem of label scarcity of the target domain by transferring the knowledge from the label rich source domain. Usually, the source domain consists of synthetic images for which the…
Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality…
We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works…
For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and…
As a specific case of graph transfer learning, unsupervised domain adaptation on graphs aims for knowledge transfer from label-rich source graphs to unlabeled target graphs. However, graphs with topology and attributes usually have…
Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…
Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the…
Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained…
Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully…
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…
Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To overcome this issue, numerous works explore Unsupervised Domain…
The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…
In this paper we present a method for line segment detection in images, based on a semi-supervised framework. Leveraging the use of a consistency loss based on differently augmented and perturbed unlabeled images with a small amount of…
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…