Related papers: We're Not Using Videos Effectively: An Updated Dom…

Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. This challenge arises due to variations in imaging…

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow…

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can…

Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask. However, language…

Semantic segmentation of nighttime images plays an equally important role as that of daytime images in autonomous driving, but the former is much more challenging due to poor illuminations and arduous human annotations. In this paper, we…

While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored. We identify that the domain gap can cause discrepancies in self-attention. Due to this gap, the…

Learning segmentation from synthetic data and adapting to real data can significantly relieve human efforts in labelling pixel-level masks. A key challenge of this task is how to alleviate the data distribution discrepancy between the…

Image segmentation is a powerful computer vision technique for scene understanding. However, real-world deployment is stymied by the need for high-quality, meticulously labeled datasets. Synthetic data provides high-quality labels while…

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…

Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acquire. Therefore, previous works pre-train their models on…

Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between…

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First,…

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…

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…

Universal domain adaptation (UniDA) transfers knowledge from a labeled source domain to an unlabeled target domain, where label spaces may differ and the target domain may contain private classes. Previous UniDA methods primarily focused on…

Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such…

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets…