Human-centered deep compositional model for handling occlusionsKoporec, Gregor (Avtor) Perš, Janez (Avtor) computer visiondeep learningconvolutional neural networkshierarchical compositional modelocclusiondiscriminabilitygeneralizabilityinterpretabilitydomain knowledgeinstance segmentationocclusion handlingDespite their powerful discriminative abilities, Convolutional Neural Networks (CNNs) lack the properties of generative models. This leads to a decreased performance in environments where objects are poorly visible. Solving such a problem by adding more training samples can quickly lead to a combinatorial explosion, therefore the underlying architecture has to be changed instead. This work proposes a Human-Centered Deep Compositional model (HCDC) that combines low-level visual discrimination of a CNN and the high-level reasoning of a Hierarchical Compositional model (HCM). Defined as a transparent model, it can be optimized to real-world environments by adding compactly encoded domain knowledge from human studies and physical laws. The new FridgeNetv2 dataset and a mixture of publicly available datasets are used as a benchmark. The experimental results show the proposed model is explainable, has higher discriminative and generative power, and better handles the occlusion than the current state-of-the-art Mask-RCNN in instance segmentation tasks.20232023-08-29 08:41:06Članek v reviji148675UDK: 004ISSN pri članku: 0031-3203DOI: 10.1016/j.patcog.2023.109397COBISS_ID: 142438403sl