Related papers: RAFT -- A Domain Adaptation Framework for RGB & Li…
Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can itself be prohibitively…
Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the available image dataset is insufficiently populated. Synthetic…
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and…
In this work, the case of semantic segmentation on a small image dataset (simulated by 1000 randomly selected images from PASCAL VOC 2012), where only weak supervision signals (scribbles from user interaction) are available is studied.…
Semantic segmentation in 3D indoor scenes has achieved remarkable performance under the supervision of large-scale annotated data. However, previous works rely on the assumption that the training and testing data are of the same…
Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative…
Achieving high-quality semantic segmentation predictions using only image-level labels enables a new level of real-world applicability. Although state-of-the-art networks deliver reliable predictions, the amount of handcrafted pixel-wise…
Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that have so far been reserved for human research…
Domain adaptation for semantic segmentation enables to alleviate the need for large-scale pixel-wise annotations. Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in…
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…
Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for…
Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…
Estimating albedo (a.k.a., intrinsic image decomposition) from single RGB images captured in real-world environments (e.g., the MVImgNet dataset) presents a significant challenge due to the absence of paired images and their ground truth…
Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby…
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training paradigm, some competitive methods have sought to the…
Robotic Perception in diverse domains such as low-light scenarios, where new modalities like thermal imaging and specialized night-vision sensors are increasingly employed, remains a challenge. Largely, this is due to the limited…
Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion.…
Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this…
There has been abundant work in unsupervised domain adaptation for semantic segmentation (DAS) seeking to adapt a model trained on images from a labeled source domain to an unlabeled target domain. While the vast majority of prior work has…
The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…