Learning to decompose for object detection and instance segmentation
This work addresses the computational complexity and hyperparameter sensitivity in object detection and instance segmentation for computer vision applications, representing a novel method rather than an incremental improvement.
The authors tackled the problem of object detection and instance segmentation by proposing an end-to-end trainable deep neural network that eliminates the need for pre- and post-processing steps like region proposals and NMS, resulting in outperforming a strong CNN baseline on synthesized digits datasets and showing promising results on KITTI car detection.
Although deep convolutional neural networks(CNNs) have achieved remarkable results on object detection and segmentation, pre- and post-processing steps such as region proposals and non-maximum suppression(NMS), have been required. These steps result in high computational complexity and sensitivity to hyperparameters, e.g. thresholds for NMS. In this work, we propose a novel end-to-end trainable deep neural network architecture, which consists of convolutional and recurrent layers, that generates the correct number of object instances and their bounding boxes (or segmentation masks) given an image, using only a single network evaluation without any pre- or post-processing steps. We have tested on detecting digits in multi-digit images synthesized using MNIST, automatically segmenting digits in these images, and detecting cars in the KITTI benchmark dataset. The proposed approach outperforms a strong CNN baseline on the synthesized digits datasets and shows promising results on KITTI car detection.