Related papers: Optimizing against Infeasible Inclusions from Data…
Recently, there have been explorations of generalist segmentation models that can effectively tackle a variety of image segmentation tasks within a unified in-context learning framework. However, these methods still struggle with task…
Models for semantic segmentation require a large amount of hand-labeled training data which is costly and time-consuming to produce. For this purpose, we present a label fusion framework that is capable of improving semantic pixel labels of…
The Segment Anything Model (SAM) exhibits a capability to segment a wide array of objects in natural images, serving as a versatile perceptual tool for various downstream image segmentation tasks. In contrast, medical image segmentation…
Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…
State-of-the-art deep neural networks demonstrate outstanding performance in semantic segmentation. However, their performance is tied to the domain represented by the training data. Open world scenarios cause inaccurate predictions which…
Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time-consuming to annotate images with semantic labels per…
One of the founding paradigms of machine learning is that a small number of variables is often sufficient to describe high-dimensional data. The minimum number of variables required is called the intrinsic dimension (ID) of the data.…
With increasing demands for high-quality semantic segmentation in the industry, hard-distinguishing semantic boundaries have posed a significant threat to existing solutions. Inspired by real-life experience, i.e., combining varied…
Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promise, they introduce inherent misalignment between generated…
Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant…
In the wake of Masked Image Modeling (MIM), a diverse range of plain, non-hierarchical Vision Transformer (ViT) models have been pre-trained with extensive datasets, offering new paradigms and significant potential for semantic…
Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic…
In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information. Recent development in deep generative models enables an efficient end-to-end framework for image…
The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem…
We introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities. Instead of attempting to impute or synthesize missing data, the proposed approach learns, for each modality, an embedding of…
We explore semantic segmentation beyond the conventional, single-dataset homogeneous training and bring forward the problem of Heterogeneous Training of Semantic Segmentation (HTSS). HTSS involves simultaneous training on multiple…
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction…
Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…
This work proves that semantic segmentation on minimally invasive surgical instruments can be improved by using training data that has been augmented through domain adaptation. The benefit of this method is twofold. Firstly, it suppresses…
This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires…