What It Does One-Shot learning can be useful when you want to identify someone just by giving the predicting model a single picture of them. Similarity Function A model can perform One-shot learning by learning a “similarity” function. When the…
Creating Templates Jinja2 is a template engine for Python which can be useful when you want to keep track of model training configuration versions. Here is one way to Implement it by combining them with a YAML file. 1. Create…
Abstract Point Pillar is an architecture proposed for 3D object detection using point clouds as inputs. Architecture The architecture consists of mainly 3 elements. Pillar Feature Net BackBone Detection Head 1. Pillar Feature Net This phase takes the following steps.…
Depth Estimation The main challenges in monocular 3D object detection lie in accurately predicting object depth. CaDDN(Categorical Depth Distribution Network) uses a predicted categorical depth distribution for each pixel to project appropriate depth in 3D space. Approaches There are several…
The 2 Stages There are mainly 2 stages when training a generative model. 1. Perceptual Compression Process of removing high-frequency details Encapsulate data into an abstract representation GANS accomplish this by projecting data from pixel space to a hyperspace called…
Types Here are some approaches to measure depth by only using RGB images from motion. Optical Expansion Observe how the length of an object changes as the camera moves closer. If the object is close, the length will dramatically change…
Objective DAFormer is an architecture proposed to improve domain adaptation for segmentation models. For the encoder, the “Hierarchical Transformer” is used due to being revealed to be robust to domain shifts. The decoder applies context-aware fusion which utilizes domain-robust context…
Unsupervised Intra-Domain Adaptation CNN-based neural networks heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically generated data are used to train segmentation models. However, models trained with these data struggle to generalize to real…
Two Frameworks There are mainly two large frameworks for training large-scale deep learning models. Data Parallelism This method is usually taken whenever your model CAN fit completely into your GPU memory, sending different batches of data for each GPU. Model…
Contrastive Learning Contrastive learning is a technique used to optimize computer-vision-related tasks by comparing multiple samples against each other to learn the attribute to identify the difference between each class.