In the single-positive multi-label (SPML) setting, each image in a dataset is labeled with the presence of a single class, while the true presence of other classes remains unknown. The challenge is to narrow the performance gap between this partially-labeled setting and fully-supervised learning, which often requires a significant annotation budget. Prior SPML methods were developed and benchmarked on synthetic datasets created by randomly sampling single positive labels from fully-annotated datasets like Pascal VOC, COCO, NUS-WIDE, and CUB200. However, this synthetic approach does not reflect real-world scenarios and fails to capture the fine-grained complexities that can lead to difficult misclassifications. In this work, we introduce the L48 dataset, a fine-grained, real-world multi-label dataset derived from recordings of bird sounds. L48 provides a natural SPML setting with single-positive annotations on a challenging, fine-grained domain, as well as two extended settings in which domain priors give access to additional negative labels. We benchmark existing SPML methods on L48 and observe significant performance differences compared to synthetic datasets and analyze method weaknesses, underscoring the need for more realistic and difficult benchmarks.

Modeling and visualizing relationships between tasks or datasets is an important step towards solving various meta-tasks such as dataset discovery, multi-tasking, and transfer learning. However, many relationships, such as containment and transferability, are naturally asymmetric and current approaches for representation and visualization (e.g., t-SNE [44]) do not readily support this. We propose TASK2Box, an approach to represent tasks using box embeddings-axis-aligned hyperrectangles in low dimensional spaces-that can capture asymmetric relation-ships between them through volumetric overlaps. We show that TASK2Box accurately predicts unseen hierarchical relationships between nodes in ImageNet and iNaturalist datasets, as well as transferability between tasks in the Taskonomy benchmark. We also show that box embeddings estimatedfrom task representations (e.g., CLIP [36], Task2Vec [4], or attribute based [15]) can be used to pre-dict relationships between unseen tasks more accurately than classifiers trained on the same representations, as well as handcrafted asymmetric distances (e.g., KL divergence). This suggests that low-dimensional box embeddings can effectively capture these task relationships and have the added advantage of being interpretable. We use the approach to visualize relationships among publicly available image classification datasets on popular dataset hosting platform called Hugging Face.

Modeling and detecting bursts in data streams is an important area of research with a wide range of applications. In this paper, we present a novel method to analyze and identify correlated burst patterns by considering multiple data streams that coevolve over time. The main technical contribution of our research is the use of a dynamic probabilistic network to model the dependency structures observed within these data streams. Such dependencies provide meaningful information concerning the overall system dynamics and should be explicitly integrated into the burst detection process. Using both synthetic scenarios and two real-world datasets, we compare our method with an existing burst-detection algorithm. Initial experimental results indicate that our approach allows for more balanced and accurate burst quantification.