2D Perception

Seeing and understanding the world in 2D

Author

Pantelis Monogioudis

CNN Example Architectures
This is a very high level view of practical structures of CNNs before the advent of more innovative architectures such as ResNets.

convolution-single-feature-map

CNN Layers
In the convolutional layer the first operation a 3D image with its two spatial dimensions and its third dimension due to the primary colors, typically Red Green and Blue is…

Faster RCNN Object Detection
With Faster RCNN, the 3rd generation in the family of region-based detectors, we are replacing the selective search algorithm that is considered computationally expensive…

Feature Extraction via Residual Networks
In the figure below we plot the top-5 classification error as a function of depth in CNN architectures. Notice the big jump due to the introduction of the ResNet architecture.

classification-detection

Introduction to Scene Understanding
In the previous chapters we have treated the perception subsystem mainly from starting the first principles that govern supervised learning to the deep learning…
 
Mask R-CNN Semantic Segmentation
The semantic segmentation approach described in this section is Mask R-CNN paper. Mask R-CNN is an extension of Faster R-CNN that adds a mask head to the detector. The mask…

object-detection-e2e

Object Detection
In the introductory section, we have seen examples of what object detection is. In this section we will treat the detection pipeline itself, summarized below:

object-detection-performance

Object Detection and Semantic Segmentation Metrics
NOTE: The following example is based on here and its corresponding implementation

Region-CNN (RCNN) Object Detection
This section describes the 1st generation of the so-called Region based CNN detectors. Despite the fact that the RCNN detector is slow and has been replaced by faster…
No matching items