Related papers: Weakly Supervised Ephemeral Gully Detection In Rem…

Modern machine learning pipelines, in particular those based on deep learning (DL) models, require large amounts of labeled data. For classification problems, the most common learning paradigm consists of presenting labeled examples during…

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…

The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients…

We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when…

Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 1$\sim$2 seconds to label one image. However, using scribble labels to learn salient object detection has not been explored.…

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…

Dimensionality reduction is often used as an initial step in data exploration, either as preprocessing for classification or regression or for visualization. Most dimensionality reduction techniques to date are unsupervised; they do not…

Wind turbine blades operate in harsh environments, making timely damage detection essential for preventing failures and optimizing maintenance. Drone-based inspection and deep learning are promising, but typically depend on large, labeled…

Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and…

The ambiguous appearance, tiny scale, and fine-grained classes of objects in remote sensing imagery inevitably lead to the noisy annotations in category labels of detection dataset. However, the effects and treatments of the label noises…

Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the problem of identifying rare examples within a corpus of…

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spurious correlations…

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

Vision-Language Models (VLMs), particularly CLIP, have revolutionized anomaly detection by enabling zero-shot and few-shot defect identification without extensive labeled datasets. By learning aligned representations of images and text,…

Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing evaluations, however, treat glitches as static visual anomalies, asking models to detect…

The detection of clouds in satellite images is an essential preprocessing task for big data in remote sensing. Convolutional neural networks (CNNs) have greatly advanced the state-of-the-art in the detection of clouds in satellite images,…

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of…

Pre-trained Vision-Language Models (VLMs) are becoming increasingly popular across various visual tasks, and several open-sourced VLM variants have been released. However, selecting the best-performing pre-trained VLM for a specific…

Gamma hadron classification, a central machine learning task in gamma ray astronomy, is conventionally tackled with supervised learning. However, the supervised approach requires annotated training data to be produced in sophisticated and…

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks…