Назад к подготовке
ВопросСредняяcomputer-visionТехническое собеседование · Navio

Вопрос

If a YOLO-style detector was trained at one image resolution, what can happen if you run inference at a different resolution? When is it technically possible?

Ответить самому

Сначала сформулируйте ответ как на собеседовании, затем откройте разбор и оцените себя.

Загрузка

Короткий ответ

It is technically possible for fully convolutional detectors, but quality can change because feature scales, anchors and small-object visibility shift. Fully connected heads may require fixed input size.

Полный разбор

Whether inference at a different resolution is technically possible depends on the architecture. A fully convolutional detector can usually accept different spatial dimensions, subject to stride divisibility and implementation constraints. If the model has fixed-size fully connected layers, those layers break unless they are replaced or adapted.

Even when the forward pass works, model quality can degrade. The detector learned feature scales, anchors, receptive-field behavior and preprocessing assumptions at the training resolution. Downscaling can hurt small objects; upscaling can change calibration and increase compute. In production, teams usually train and validate on the same resolution used for deployment or run explicit multi-scale training/evaluation.

For an automotive perception role, the stronger answer connects resolution choices to latency, hardware budget and safety-critical recall.

Теория

Shape compatibility and metric stability are separate questions.

Типичные ошибки

  • Assume any CNN accepts any resolution with no metric change.
  • Forget stride and head constraints.
  • Discuss only speed and not detection quality.

Как отвечать на собеседовании

  • Start with architecture compatibility.
  • Then discuss quality and deployment tradeoffs.