Why can a detector run out of memory on crowded images but not equally large sparse images?
Computer VisionLevel: AdvancedDense-scene target assignment memory
Why can a detector run out of memory on crowded images but not equally large sparse images?
Hints
- Image resolution is not the only size-dependent dimension.
- How large is the candidate-by-ground-truth overlap matrix?
Answer
This answer is part of mentoring
Advanced questions come with a full breakdown and a mock interview with a working quant researcher. The first call is free.
Source and licence: OpenMMLab — MMDetection FAQ · Apache-2.0 · answer: Quantoros editorial