-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Laskar_2025_CVPR, author = {Laskar, Zakaria and Vojir, Tomas and Grcic, Matej and Melekhov, Iaroslav and Gangisetty, Shankar and Kannala, Juho and Matas, Jiri and Tolias, Giorgos and Jawahar, C.V.}, title = {A Dataset for Semantic Segmentation in the Presence of Unknowns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2025}, pages = {1439-1448} }
A Dataset for Semantic Segmentation in the Presence of Unknowns
Abstract
Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalies). This is especially important for scene understanding tasks with safety critical applications, such as in autonomous driving. Existing datasets allow evaluation of only either knowns or unknowns - but not both, which is required to establish "in the wild" suitability of deep neural network models. To bridge this gap, we propose a novel anomaly segmentation dataset, ISSU, featuring a diverse set of anomaly inputs from cluttered real-world environments. The dataset is twice larger than existing anomaly segmentation datasets, and provides a training, validation and test set for controlled in-domain evaluation. The test set consists of a static and temporal part, with the later comprised of videos. The dataset provides annotations for both closed-set (knowns) and anomalies, enabling closed-set and open-set evaluation. The dataset covers diverse conditions, such as domain and cross-sensor shift, illumination variation and allows ablation of anomaly detection methods with respect to these variations. Evaluation results of current state-of-the-art methods confirm the need for improvements especially in domain-generalization, small and large object segmentation. The benchmarking code and the dataset will be made available.
Related Material