Non-Separable Multi-Dimensional Network Flows for Visual Computing
This work addresses limitations in expressiveness for computer vision tasks like multi-object tracking, offering an incremental improvement over scalar flow methods.
The paper tackles the loss of information in scalar-valued network flows for computer vision by proposing a non-separable multi-dimensional network flow formalism, which enables adaptive feature selection and demonstrates improved robustness to noise on the MOT16 benchmark.
Flows in networks (or graphs) play a significant role in numerous computer vision tasks. The scalar-valued edges in these graphs often lead to a loss of information and thereby to limitations in terms of expressiveness. For example, oftentimes high-dimensional data (e.g. feature descriptors) are mapped to a single scalar value (e.g. the similarity between two feature descriptors). To overcome this limitation, we propose a novel formalism for non-separable multi-dimensional network flows. By doing so, we enable an automatic and adaptive feature selection strategy - since the flow is defined on a per-dimension basis, the maximizing flow automatically chooses the best matching feature dimensions. As a proof of concept, we apply our formalism to the multi-object tracking problem and demonstrate that our approach outperforms scalar formulations on the MOT16 benchmark in terms of robustness to noise.