Semantic segmentation with Convolutional Neural Network Approaches

Editor's Notes

• #4: Microsoft Common Objects in Context (COCO) [31]6 : is another image recognition, segmentation, and captioning large-scale dataset. It features various challenges, being the detection one the most relevant for this field since one of its parts is focused on segmentation. That challenge, which features more than 80 classes, provides more than 82783 images for training, 40504 for validation, and its test set consist of more than 80000 images. In particular, the test set is divided into four different subsets or splits: test-dev (20000 images) for additional validation, debugging, test-standard (20000 images) is the default test data for the competition and the one used to compare state-of-the-art methods, testchallenge (20000 images) is the split used for the challenge when submitting to the evaluation server, and test-reserve (20000 images) is a split used to protect against possible overfitting in the challenge (if a method is suspected to have made too many submissions or trained on the test data, its results will be compared with the reserve split). Its popularity and importance has ramped up since its appearance thanks to its large scale. In fact, the results of the challenge are presented yearly on a joint workshop at the European Conference on Computer Vision (ECCV)7 together with ImageNet’s ones
• #5: Instance segmentation is challenging because it requires the correct detection of all objects in an image while also precisely segmenting each instance. It therefore combines elements from the classical computer vision tasks of ob- ject detection , where the goal is to classify individual ob- jects and localize each using a bounding box, and semantic RoIAlign RoIAlign class box conv conv conv conv Figure 1. The Mask R-CNN framework for instance segmentation. segmentation , where the goal is to classify each pixel into a fixed set of categories without differentiating object in- stances
• #6: Mask R-CNN is conceptually simple: Faster R-CNN has two outputs for each candidate object, a class label and a bounding-box offset; to this we add a third branch that out- puts the object mask. Mask R-CNN is thus a natural and in- tuitive idea. But the additional mask output is distinct from the class and box outputs, requiring extraction of much Finer spatial layout of an object RoIPool [12] is a standard operation for extract- ing a small feature map ( e.g ., 7 × 7) from each RoI. RoIPool first quantizes a floating-number RoI to the discrete granu- larity of the feature map,.
• #7: Mask R-CNN also outputs a binary mask for each RoI. This is in contrast to most recent systems, where clas- Sification dependson mask predictions
• #8: aster R-CNN consists of two stages. The first stage, called a Region Proposal Network (RPN), proposes candidate object bounding boxes.
• #11: Convolution layers retain the spatial oreintation and such information
• #14: Speed: Artous convolution in the deepLab v2 and applying the dense deep convolution neural net- work reduce the performance of video run-time from 0.5 second per frame in DeepLabv1 to 8fps in deepLabv2. Accuracy: due to extracting the dense feature extrac- tion in DeepLab v2, this model has higher accuracy in the detection and segmentation tasks. Simplicity: applying the atrous convolution and other novel techniques that are utilized in this mod- els made it more simple
• #18: 1464 and 1449 images