Annotation means any extra information that is attached to the data.
In the machine learning domain, it refers to assigning predefined categories and tags/labels to documents and images. This data-label pair can be used for training classification-related problems by supervised learning where finding hidden patterns is easy.
In deep learning, backpropagation is one of the two sub-processes of the training process, which adjust the parameters of the forward propagation with respect to the error it produces.
Backpropagation stands for “backward propagation of errors”. It refers to the algorithm used for training feedforward neural networks by repeatedly adjusting the network’s weights to minimize the difference between the actual output vector of the net and the desired output vector.
Backpropagation aims to minimize the cost function by adjusting the network’s weights and biases. The cost function gradients determine the level of adjustment concerning parameters like activation function, weights, bias, etc.
COCO is an image dataset composed of 90 different classes of objects (cars, persons, sports balls, bicycles, dogs, cats, horses e.t.c). The dataset was gathered to solve common object detection problems.
Convolutional Neural Networks also known as ConvNets are a type of Feed-Forward Neural networks used in tasks like image analysis, natural language processing, or other complex image classification problems.
Dataset is a collection of meaningful data which the machine sees and learns.
Dataset may contain raw information in the form of images, tabular data, signals, videos etc that helps derive inferences. An example is a tabular set of data where each column defines attributes/characteristics of the data and each row is a tuple/record in the dataset.
Ensemble Learning is a method of reaching a consensus in predictions by fusing the salient properties of two or more models.
The final ensemble learning framework is more robust than the individual models that constitute the ensemble because ensembling reduces the variance in the prediction errors. Ensemble Learning tries to capture complementary information from its different contributing models—that is, an ensemble framework is successful when the contributing models are statistically diverse.
In deep learning, feedforward propagation is one of the two sub-processes of the training process, which builds correlation by assigning parameters.
Feedforward Propagation occurs when the input data is fed in the forward direction through the network. Each hidden layer receives the input data, processes it (using an Activation Function), and passes it onto the next layer.
In the feedforward propagation, the Activation Function is a mathematical “gate” in between the input feeding the current neuron and its output going to the next layer.
Image Preprocessing are the steps we take to convert a raw image into an enhanced form that the model is ready to use for training and inference.
The images collected for any computer vision tasks may be of different sizes, contrast, orientation. Image Preprocessing involves all the deterministic steps that we take to make the images all formatted correctly.
Instance segmentation models classify pixels into categories on the basis of “instances” rather than classes.
An instance segmentation algorithm has no idea of the class a classified region belongs to but can segregate overlapping or very similar object regions on the basis of their boundaries.
If the same image of a crowd we talked about before is fed to an instance segmentation model, the model would be able to segregate each person from the crowd as well as the surrounding objects (ideally), but would not be able to predict what each region/object is an instance of.
Object tracking is a deep learning process where the algorithm tracks the movement of an object. In other words, it is the task of estimating or predicting the positions and other relevant information of moving objects in a video.
Object tracking usually involves the process of object detection. Here’s a quick overview of the steps:
Object detection, where the algorithm classifies and detects the object by creating a bounding box around it.
Assigning unique identification for each object (ID).
Tracking the detected object as it moves through frames while storing the relevant information.
Panoptic segmentation can be expressed as the combination of semantic segmentation and instance segmentation where each instance of an object in the image is segregated and the object’s identity is predicted.
Panoptic segmentation algorithms find large-scale applicability in popular tasks like self-driving cars where a huge amount of information about the immediate surroundings must be captured with the help of a stream of images.
Unsupervised Learning is a type of machine learning in which the algorithms are provided with data that does not contain any labels or explicit instructions on what to do with it.
The goal is for the learning algorithm to find structure in the input data on its own.
To put it simply—Unsupervised Learning is a kind of self-learning where the algorithm can find previously hidden patterns in the unlabeled datasets and give the required output without any interference.
Identifying these hidden patterns helps in clustering, association, and detection of anomalies and errors in data.