Non-Max Suppression is a post-processing method for object detection tasks. In most cases, an object detection model will predict multiple boxes for a single object like the picture in my note. However, we don’t want this crowded output. We instead…
Background Most of the previous semantic segmentation model’s architecture can be categorized into 2 types. Encoder-Decoder Backbone: (Ex. FCN, UNet) This architecture requires all information to flow through the deep encoding-decoding structure leading to high latency, also suffering in restoring…
Hessian Matrix packages all the information of the second derivative of a function. This matrix can be used to determine saddle points or the local extremum of a function.
Bayes Theorem Bayes Theorem is about considering the posterior distribution considering prior distribution and currently available data. Let’s say we want to predict a man’s occupation. Is this man a librarian or a farmer given the following description? – He…
DBScan Density-Based Scan is a clustering method recommended when clusters are nested. You first specify 2 parameters. 1. Radius 2. Number of points to be considered as “core” points. Algorithm The algorithm takes the following steps. 1. Within the radius,…
Pruning “Pruning” means sparsing the network for faster inference. Most of the weights inside networks are quite useless, so this can help when you have limited resources such as running inference on the edge. Methods There are mainly 2 methods…
Here is a simple diagram of understanding the meaning of each error rate gaps.
There are 2 ways to consider “depth” for models.
Here is a simple guide to consider what you need to do next to improve your model’s performance.
Selective Search Selective search is a region proposal method for object detection. It hierarchically groups similar regions based on color, texture, size, and shape. Selective Search uses over-segmented images as input. Then takes the following steps. 1. Add all bounding…