Bài kiểm tra có liên kết hướng dẫn · Trung bình Cấp độ

Bài kiểm tra giải thích về phân loại hình ảnh

Kiểm tra phân loại một nhãn và nhiều nhãn, ranh giới phát hiện, học chuyển giao, đánh giá nhóm, hiệu chuẩn và đầu vào không chắc chắn.

Đường dẫn hướng dẫn liên quanGiải thích về phân loại hình ảnh
Câu hỏi 1 của 8

A model labels a whole photo “bicycle.” What does classification alone leave unresolved?

Xem trước mọi câu hỏi8 câu hỏi

Câu trả lời và giải thích xuất hiện khi bạn làm bài kiểm tra.

  1. A model labels a whole photo “bicycle.” What does classification alone leave unresolved?
    • Where the bicycle is in the image
    • Which label was selected from its vocabulary
    • Whether the prediction score can be displayed
    • Whether a class label can be assigned to the crop
  2. A street scene contains a bus and bicycle. Which output setup can represent both as present?
    • One mutually exclusive softmax over the scene
    • A location box without a multi-label head
    • One dominant-category tag only
    • Independent multi-label outputs
  3. Why can a classifier label an unfamiliar object confidently as a known class?
    • A high score guarantees a familiar object
    • Its output is restricted to learned labels and may not represent “none of these”
    • Transfer learning adds every unseen class automatically
    • The largest score is validated as an unknown-class detector
  4. A team has few labeled photos for a new task. Which transfer-learning approach is documented?
    • Discard pretrained weights before every small-data task
    • Change only display names without fitting a classifier
    • Reuse a pretrained feature extractor and train a new final classifier
    • Tune only on final test photos
  5. Why group photos of the same physical item into one partition during evaluation?
    • Near duplicates across train and test can inflate the score
    • It guarantees each class is equally frequent
    • It makes camera calibration unnecessary
    • It changes classification into instance segmentation
  6. A product rejects good items more often than bad ones. Which report helps diagnose this?
    • Only the total dataset image count
    • Only the architecture layer count
    • Only the highest model confidence
    • Per-class errors and false-positive/false-negative counts
  7. When can a displayed 0.9 class score be treated as a calibrated 90% success estimate?
    • Whenever a softmax layer exists
    • Only after held-out calibration evidence supports that interpretation
    • Whenever image resolution is high
    • Whenever the network has many parameters
  8. What helps with an input that fits none of the trained classes?
    • Always choose a known class with full certainty
    • Add a new display label without training or validation
    • An abstain or human-review route based on tested criteria
    • Assume every unfamiliar photo is a camera failure