Teacher since August 2025
Noor Siddiqui
Computer vision taught through real images, real failure cases and careful evaluation
9
tutors built
4.5Sample
average from 21 reviews
406Sample
lessons taught by their tutors
About Noor
I teach computer vision: classification, detection, segmentation, document understanding, video and the newer models that combine images with language. Most of my work has been building vision systems that had to hold up outside the lab, under odd lighting, unusual cameras and labels that were not quite consistent. So my lessons spend as much time on data and evaluation as on architectures. I like to put an image on the table and ask what the model would need to notice to get it right, then look at where real models fail. I keep the maths light unless you want more, and I am honest about what vision models still cannot do.
Knows about
Tutors by Noor
9 tutors
Object detection explained
Understand boxes, IoU, NMS and mAP well enough to train, evaluate and debug a detector75 lessonsSampleNoor Siddiqui$8Image embeddings and visual searchImage embeddings and visual search
Build image similarity and text to image search, and measure whether results are actually relevant71 lessonsSampleNoor Siddiqui$7Image classification, first principlesImage classification, first principles
Plan, train and honestly evaluate an image classifier, from defining classes to studying its mistakes64 lessonsSampleNoor SiddiquiFreeVision language models: what they seeVision language models: what they see
Know how AI models read images, what they get right and wrong, and how to check their answers61 lessonsSampleNoor Siddiqui$6OCR and document understandingOCR and document understanding
Understand how machines read scans, forms and tables, and how to check that they read correctly51 lessonsSampleNoor Siddiqui$5Data augmentation for visionData augmentation for vision
Choose image augmentations that reflect real variation, keep labels correct and improve generalisation44 lessonsSampleNoor Siddiqui$4Image segmentation: semantic, instance, panopticImage segmentation: semantic, instance, panoptic
Label every pixel correctly: understand the three kinds of segmentation, their models and metrics40 lessonsSampleNoor Siddiqui$8Vision transformers in depthVision transformers in depth
Understand patch tokens, position embeddings, data needs and compute trade offs in vision transformersNoor Siddiqui$12Video understanding basicsVideo understanding basics
Learn how models handle time in video, from frame sampling to action recognition and trackingNoor Siddiqui$5Recent reviews
What students said about Noor's tutors.
- Ravi K.Sample
Tiling large drone images for small objects was exactly what I needed. Also found missing labels in my set thanks to the last lesson.
- Kofi A.Sample
The privacy lesson was taken seriously, not tacked on. Helped me push back on a face matching feature request at work.
- Joao F.Sample
Looking at raw predictions before NMS showed my crowd problem immediately. The IoU exercises made the threshold settings make sense.
- Mark T.Sample
Clear metric lessons. The tip to never compare Dice with IoU saved me from a misleading slide in a team meeting.
- Lucia M.Sample
The error analysis lesson changed how I work. Tagging 50 failures showed that a third were labelling mistakes from my own team, not model problems.
- Bongani T.Sample
The totals check idea caught 14 misread receipts in my first batch. I had assumed the output was fine because it looked so tidy.