The most common approaches to instance segmentation are complex and use two-stage networks with object proposals, conditional random-fields, template matching or recurrent neural networks.
Most contemporary approaches to instance segmentation use complex pipelines involving conditional random fields, recurrent neural networks, object proposals, or template matching schemes.
Ranked #8 on Instance Segmentation on Cityscapes test
We propose a deep learning-based solution for the problem of feature learning in one-class classification.
Unlike previous algorithms that compress the data with PCA, KiloSort operates on the raw data which allows it to construct a more accurate model of the waveforms.
Finding a template in a search image is one of the core problems many computer vision, such as semantic image semantic, image-to-GPS verification \etc.
We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template.
In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations.
Ranked #2 on Visual Object Tracking on OTB-2015 (Precision metric)