Related papers: Self-Supervised Pretraining on Satellite Imagery: …
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e.g., unlabeled LiDAR…
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide…
New advancements in radio data post-processing are underway within the SKA precursor community, aiming to facilitate the extraction of scientific results from survey images through a semi-automated approach. Several of these developments…
Mobile robots operating in unknown urban environments encounter a wide range of complex terrains to which they must adapt their planned trajectory for safe and efficient navigation. Most existing approaches utilize supervised learning to…
The success of existing salient object detection models relies on a large pixel-wise labeled training dataset, which is time-consuming and expensive to obtain. We study semi-supervised salient object detection, with access to a small number…
Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn…
Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore,…
The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…
We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. Unlike prior self-supervised approaches which often involve geometric augmentations on the image…
Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, many regions around the world face challenges due to outdated,…
Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…
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…
Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…
In recent years, driven by the need for safer and more autonomous transport systems, the automotive industry has shifted toward integrating a growing number of Advanced Driver Assistance Systems (ADAS). Among the array of sensors employed…
The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded…
Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…
Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis. This paper studies the…
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…