Intro to Semantic Segmentation Using Deep Learning
0 likes128 views
The document introduces semantic segmentation, a deep learning task that classifies each pixel in an image into different classes, contrasting it with instance segmentation. It highlights the importance of pixel-level understanding for applications like self-driving cars and robotic systems, and discusses the Fully Convolutional Network (FCN) model architecture used for this task. The FCN processes images through down sampling and up sampling to maintain semantic and spatial information, utilizing skip connections to aid in feature merging.
Intro to Semantic Segmentation Using Deep Learning
- 1. Intro to Semantic Segmentation Using Deep Learning ================================================================ Semantic segmentation is the task of classifying each and every pixel in an image into a class as shown in the image below. Here you can see that all persons are red, the road is purple, the vehicles are blue, street signs are yellow etc. Semantic segmentation is different from instance segmentation which is that different objects of the same class will have different labels as in person1, person2 and hence different colours. The picture below very crisply illustrates the difference between instance and semantic segmentation. If you are interested in learning more about classification and object detection, please check out my blog here.
- 2. One important question can be why do we need this granularity of understanding pixel by pixel location? Some examples that come to mind are: i) Self Driving Cars — May need to know exactly where another car is on the road or the location of a human crossing the road ii) Robotic systems — Robots that say join two parts together will perform better if they know the exact locations of the two parts iii) Damage Detection - It may be important in this case to know the exact extent of damage Deep Learning Model Architectures for Semantic Segmentation Lets now talk about 3 model architectures that do semantic segmentation. 1. Fully Convolutional Network (FCN) FCN is a popular algorithm for doing semantic segmentation. This model uses various blocks of convolution and max pool layers to first decompress an image to 1/32th of its original size. It then makes a class prediction at this level of granularity. Finally it uses up sampling and deconvolution layers to resize the image to its original dimensions. These models typically don't have any fully connected layers. The goal of down sampling steps is to capture semantic/contextual information while the goal of up sampling is to recover spatial information. Also there are no limitations on image size. The final image is the same size as the original image. To fully recover the fine grained spatial information lost in down sampling, skip connections are used. A skip
- 3. connection is a connection that bypasses at least one layer. Here it is used to pass information from the down sampling step to the up sampling step. Merging features from various resolution levels helps combining context information with spatial information Contacts Us:- Address: - 110 Fontainbleau Drive, Toronto Telephone: - 647-550-0256 Email: - [email protected]