Related papers: Community-aware evaluation and threshold calibrati…
Citizen science biodiversity data present great opportunities for ecology and conservation across vast spatial and temporal scales. However, the opportunistic nature of these data lacks the sampling structure required by modeling…
Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalization of zero-shot learning, where the new classes are not known…
Reliable confidence estimation is a challenging yet fundamental requirement in many risk-sensitive applications. However, modern deep neural networks are often overconfident for their incorrect predictions, i.e., misclassified samples from…
In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object…
This report provides a detailed description of the method we explored and proposed in the OSR Challenge at the OOD-CV Workshop during ECCV 2024. The challenge required identifying whether a test sample belonged to the semantic classes of a…
Multi-Object Tracking (MOT) is a crucial computer vision task that aims to predict the bounding boxes and identities of objects simultaneously. While state-of-the-art methods have made remarkable progress by jointly optimizing the…
Plankton provide the foundation for life on earth. To advance our understanding of the marine ecosystem, for scientific, commercial and survival purposes, more in situ continuous monitoring and analysis of plankton is required. Cost,…
The re-emergence of mosquito-borne diseases (MBDs), which kill hundreds of thousands of people each year, has been attributed to increased human population, migration, and environmental changes. Convolutional neural networks (CNNs) have…
Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image. This is unfortunate as occlusion boundaries are important cues to recognize…
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…
In deep, ground-based imaging, about 15%-30% of object detections are expected to correspond to two or more true objects - these are called ``unrecognized blends''. We use Machine Learning algorithms to detect unrecognized blends in deep…
We present an approach for automated in-situ monitoring of phytoplankton and zooplankton communities based on a dual magnification dark-field imaging microscope/camera. We describe the Dual Scripps Plankton Camera (DSPC) system and…
In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set…
Recent large vision-language models such as CLIP have shown remarkable out-of-distribution (OOD) detection and generalization performance. However, their zero-shot in-distribution (ID) accuracy is often limited for downstream datasets.…
Remote sensing of the Earth's surface water is critical in a wide range of environmental studies, from evaluating the societal impacts of seasonal droughts and floods to the large-scale implications of climate change. Consequently, a large…
A critical vulnerability of supervised deep learning in high-dimensional tabular domains is "generalization collapse": models form precise decision boundaries around known training distributions but fail catastrophically when encountering…
Open-set semi-supervised learning (OSSL) leverages practical open-set unlabeled data, comprising both in-distribution (ID) samples from seen classes and out-of-distribution (OOD) samples from unseen classes, for semi-supervised learning…
The spatial transcriptomics (ST) data produced by recent biotechnologies, such as CosMx and Xenium, contain huge amount of information about cancer tissue samples, which has great potential for cancer research via detection of community: a…
Phytoplankton parasites are largely understudied microbial components with a potentially significant ecological impact on phytoplankton bloom dynamics. To better understand their impact, we need improved detection methods to integrate…
Online Social Communities (OSCs) provide a medium for connecting people, sharing news, eliciting information, and finding jobs, among others. The dynamics of the interaction among the members of OSCs is not always growth dynamics. Instead,…