CNNs don’t always have to progressively decrease resolution. A revolutionary idea that might shape the next-gen architectures for Computer Vision. — TL;DR: Transformers(NLP): Isotropic architecture+Self-attention ViT: Transformers(NLP)+Patch representation CNNs: Pyramid architecture(decreasing resolution)+Convolution ConvMixer: Isotropic architecture+Patch representation+Convolution Transformers are represented by the extensive use of attention and their isotropic architecture, which repeats the same block multiple times. They demonstrated amazing performance for many problems, especially in natural language processing. However, the…

In-depth review on Basic, Transposed, Dilated, Separable, Depthwise, and Pointwise convolutions and their applications. — Recent research on CNN architectures include so much different variants of convolutions that confused me while reading these papers. I thought it would be worth it to go through the precise definitions, effects, and use cases(in computer vision & deep-learning) of some of the more popular convolution variants. These variants…

Deep-learning is used everywhere, but they often overfit the training data and are not generalizable to unseen samples. Various regularization techniques prevent such overfitting. Dropout is one of the most popular and powerful regularization techniques, used regardless of network architecture and type of task. …

VGG is considered one of the cornerstones of deep CNNs. The authors of VGG provided widely accepted principles for designing CNNs. In particular, they suggest that multiple 3 × 3 convolutions are more efficient than using larger kernel sizes. However, the VGG architecture, composed of nothing but successive stacks of…

Object detection is a complex problem in computer vision that involves localizing and classifying multiple objects from a given image. It is one of the most practically important and widely researched problem in computer vision. There is a wide variety of approaches to object detection including deep-learning based methods. These…

Work in progress… — This article is a work-in progress that will grow as I read articles and learn more about the various aspects of deep-learning based cell microscopy and oncology. We will discuss the characteristics and previous works on several problems that deep-learning based approaches are used in these fields. Disclaimer: I don’t…

Real-world images commonly experience various degradations throughout their lifetime. For example, images taken using older devices include various noise and artifacts. Artifacts are also added when images experience multiple editing and compressions while being shared and transferred multiple times using the internet. However, recovering from such degradation and bringing these…

We will implement a series of two-stage object detection algorithms from the initial works of R-CNN to state-of-the-art techniques such as DetectoRS from scratch using PyTorch. This article is the first post on this series, and we will discuss the implementations of various components in the object detection pipeline. …

There have been many experiments on the search for the most efficient CNN architecture. An efficient architecture must find a perfect balance between many bottlenecks such as accuracy, parameters, FLOPs, or inference time. Many papers focus on different bottlenecks according to their needs. For example, DenseNet and EfficientNet try to…