When starting an object detection project, the initial focus is often on building the most accurate model possible. However, highly accurate models are usually not deployable in production scenarios due to the trade-off between accuracy and computational demands. These models tend to be resource-intensive and can be impractical and costly to deploy. Deploying models on ..read more

The world of computer vision changed forever 2011 onwards, when convolutional neural networks (CNNs) revolutionized object detection by providing a significant leap in accuracy and efficiency compared to earlier methods like the Viola-Jones framework, which primarily relied on handcrafted features and boosted classifiers.    CNN-based models like Faster R-CNN, YOLO, and CenterNet brought about groundbreaking ..read more

Building ReceiptNinja: An Intelligent Receipt Processing Demo App In today’s digital-first world, managing receipts—whether physical or digital—can be a daunting task for individuals and businesses alike. Manual data entry for expense tracking or finance management is time-consuming, error-prone, and tedious. Enter ReceiptNinja, an intelligent demo application designed to automate this process by extracting key fields ..read more

Tex  to Image models like DALL-E, Imagen, and Stable Diffusion have attracted a lot of attention to Image Synthesis models, recently. These models can generate impressive looking images from benign looking prompts. Here are a few typical examples of images from Stable Diffusion:                 Looking under the hood ..read more

MOTR is a state of the art end-to-end multiple object tracker that does not require any temporal association between objects of adjacent frames. It directly outputs the track of objects in a sequence of input images (video). MOTR uses Deformable DETR for object detection on a single image. To understand the architecture of MOTR it ..read more

GhostNetV2 is a recent SOTA architecture that allows an implementation of Long-Range attention in the deep CNN frameworks used in various ML tasks such as image classification, object detection, and video analysis. GhostNetV2 proposes a new attention mechanism called DFC attention to capture long range spatial information. And it does so while keeping the implementation ..read more

CLIP By OPEN-AI Introduction Nearly all state-of-the-art visual perception algorithms rely on the same formula:  (1) pretrain a convolutional network on a large, manually annotated image classification dataset (2) finetune the network on a smaller, task-specific dataset. This technique has been widely used for several years and has led to impressive improvements on numerous tasks.  ..read more

Machine Learning Reality Check In the Machine Learning World or broadly in the AI Universe, the colonists such as Data Scientists, Machine Learning Engineers, Deep Learning Specialist are coached towards a belief i.e. “More Training Data Means Highly Accurate Production Model“. Which to some extent is unavoidably true but predominately it’s also a fact, that ..read more

Introduction Photo-realistic image rendering using standard graphics techniques requires realistic simulation of geometry and light. The algorithms which we use currently for the task are effective but expensive. If we were able to render photo-realistic images using a model learned from data, we could turn the process of graphics rendering into a model learning and ..read more

Introduction Images produced by generative methods have been improving lately. Most of the recent generative algorithms have made use of generative networks that are trained using a discriminator network as their adversary. Generative Adversarial Networks (GANs) or generators, in other words, are a relatively new concept in the field of computer vision. Their aim is ..read more