Overview
What this challenge is about.
Scene-Graph Generation for Retail Shelf Audits. Advanced challenge in code. Writing production code that solves real engineering problems, earn a blockchain-...
The Brief
What you'll do, and what you'll demonstrate.
Build a scene-graph generation pipeline for shelf photos and prove (or disprove) that scene graphs unlock insights a detector-only baseline cannot.
This is not a coding exercise. It is the work a software engineer does between a Jira ticket and a merged PR. That distinction matters to every hiring manager who has seen candidates solve LeetCode problems and none who have shipped production code under real constraints.
When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."
Earning criteria — what you'll demonstrate
- Implement a scene-graph generation pipeline combining detection and relation prediction
- Apply scene-understanding metrics (recall@K of relations) honestly
- Reason about when a richer representation actually unlocks downstream value
- Communicate computer-vision results to a product audience without jargon
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Scene Graph Generation
Apply scene graph generation to solve real industry problems and demonstrate production-level capability.
- Object Detection
Apply object detection to solve real industry problems and demonstrate production-level capability.
- Relation Prediction
Apply relation prediction to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Scene Understanding
Apply scene understanding to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Computer Vision Engineer
Shipping a scene-graph pipeline beyond plain detection is exactly the next-step work CV engineers do at any analytics company moving from 'what's in the photo' to 'what's the story'.
This challenge sharpens
- scene-graph-generation
- object-detection
- relation-prediction
Applied AI Scientist
Comparing a richer representation against a baseline on real downstream questions is the day-to-day applied AI scientist's job for any product team weighing model upgrades.
This challenge sharpens
- scene-understanding
- evaluation
- relation-prediction
Machine Learning Engineer
Building a detector-plus-head pipeline and operating it on a labeled holdout with reproducible reporting maps directly to MLE work in computer-vision-heavy products.
This challenge sharpens
- object-detection
- pytorch
- evaluation