相关论文: Improving EO Foundation Models with Confidence Ass…

Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision. These foundation vision…

Optical Coherence Tomography (OCT) is essential for diagnosing conditions such as glaucoma, diabetic retinopathy, and age-related macular degeneration. Accurate retinal layer segmentation enables quantitative biomarkers critical for…

Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM),…

Automated audio captioning models frequently produce overconfident predictions regardless of semantic accuracy, limiting their reliability in deployment. This deficiency stems from two factors: evaluation metrics based on n-gram overlap…

Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels. However, most approaches struggle to produce accurate localization maps…

Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO…

While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence…

Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most…

The rapid development of deep learning has driven significant progress in image semantic segmentation - a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e.,…

Deep learning has revolutionized various fields by enabling highly accurate predictions and estimates. One important application is probabilistic prediction, where models estimate the probability of events rather than deterministic…

In semantic segmentation, the accuracy of models heavily depends on the high-quality annotations. However, in many practical scenarios, such as medical imaging and remote sensing, obtaining true annotations is not straightforward and…

Semantic segmentation is the task of assigning a label to each pixel in the image.In recent years, deep convolutional neural networks have been driving advances in multiple tasks related to cognition. Although, DCNNs have resulted in…

In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS). Previously, with the well-known open-set semantic segmentation (OSS), the intelligent agent only detects the…

This paper investigates methods for estimating uncertainty in semantic segmentation predictions derived from satellite imagery. Estimating uncertainty for segmentation presents unique challenges compared to standard image classification,…

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label…

While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems…

Land Use and Land Cover (LULC) mapping is a fundamental task in Earth Observation (EO). However, current LULC models are typically developed for a specific modality and a fixed class taxonomy, limiting their generability and broader…

A key ethical challenge in Automated Essay Scoring (AES) is ensuring that scores are only released when they meet high reliability standards. Confidence modelling addresses this by assigning a reliability estimate measure, in the form of a…