Related papers: S^4M: Boosting Semi-Supervised Instance Segmentati…
Partial Label (PL) learning refers to the task of learning from the partially labeled data, where each training instance is ambiguously equipped with a set of candidate labels but only one is valid. Advances in the recent deep PL learning…
The limited availability of labeled data has driven advancements in semi-supervised learning for medical image segmentation. Modern large-scale models tailored for general segmentation, such as the Segment Anything Model (SAM), have…
Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…
Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…
Remote sensing data is crucial for applications ranging from monitoring forest fires and deforestation to tracking urbanization. Most of these tasks require dense pixel-level annotations for the model to parse visual information from…
This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box…
Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they…
Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…
In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partially annotated data…
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tackle the problem, they…
Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…
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…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
Semi-supervised learning, which leverages both annotated and unannotated data, is an efficient approach for medical image segmentation, where obtaining annotations for the whole dataset is time-consuming and costly. Traditional…
Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem…
Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled…
In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…
We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method is featured with 1) the exponential moving averaging strategy to update the teacher from the student…
The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose…