UNIT 016 h allocated
Image datasets
- Annotation rules
- provenance
- group splits
- augmentation
← Course catalogue
DEEP LEARNING & PERCEPTION / SPECIALIST
CV320Computer vision: detection & segmentation
24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief
Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.
BEFORE YOU BEGIN
A clear starting point.
Prerequisites: DL301
Specialist studio; environment and faculty must be confirmed before scheduling
WHAT YOU SHOULD BE ABLE TO DEMONSTRATE
- Explain the assumptions and failure modes in image datasets.
- Complete the practical: fine-tune a small approved vision model and analyse localisation or segmentation failures.
- Defend the resulting annotation guide with reproducible evidence.
THE SUBJECTS / FOUR CONNECTED UNITS
What you will study.
UNIT 026 h allocated
Detection
- Bounding boxes
- localisation
- IoU
- nonmaximum suppression
UNIT 036 h allocated
Segmentation
- Pixel labels
- masks
- class imbalance
- boundary errors
UNIT 046 h allocated
Evaluation
- mAP concepts
- class-wise errors
- domain shift
- inference limits
THE TRAINING STUDIO
Make the subject
visible in your work.
Fine-tune a small approved vision model and analyse localisation or segmentation failures.
Evidence to produce
- Annotation guide
- held-out benchmark
- failure gallery
Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.
ASSESS THE REASONING
A question you
should be able to answer.
Why can adjacent video frames in train and test produce a misleading score?
Review dimensions
Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.
External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.