Related papers: Building-Guided Pseudo-Label Learning for Cross-Mo…

In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique…

Deep learning-based medical image segmentation typically relies on ground truth (GT) labels obtained through manual annotation, but these can be prone to random errors or systematic biases. This study examines the robustness of deep…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting…

Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning. In this setting, users design heuristics that provide noisy labels for subsets of the…

Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…

Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning…

Buildings classification using satellite images is becoming more important for several applications such as damage assessment, resource allocation, and population estimation. We focus, in this work, on buildings damage assessment (BDA) and…

FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey. The dataset presents a unique challenge of advancing the damage assessment process for post-disaster scenarios…

Estimating the number of buildings in any geographical region is a vital component of urban analysis, disaster management, and public policy decision. Deep learning methods for building localization and counting in satellite imagery, can…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

Purpose: Deep neural networks (DNNs) have been widely applied in medical image classification, benefiting from its powerful mapping capability among medical images. However, these existing deep learning-based methods depend on an enormous…

Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-supervised learning methods consists in the effective use of…

We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…

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…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervised learning addresses this dilemma by leveraging unlabeled…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Accurate training labels are a key component for multi-class medical image segmentation. Their annotation is costly and time-consuming because it requires domain expertise. This work aims to develop a dual-branch network and automatically…