Kuiz berkaitan panduan · Sederhana Tahap

Kuiz Pengesanan Objek Perbendaharaan Kata Terbuka

Semak pengesanan wilayah bersyarat teks, pralatihan teks imej, gesaan kategori novel, penyetempatan dan keperluan untuk menilai anotasi yang dijana.

soalan 1 daripada 8

Apakah keupayaan menentukan pengesanan objek perbendaharaan kata terbuka?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Apakah keupayaan menentukan pengesanan objek perbendaharaan kata terbuka?
    • Mengesan hanya kategori yang dilihat dengan kotak semasa latihan
    • Berjalan lebih pantas daripada semua pengesan lain
    • Mengesan objek yang diterangkan oleh teks sewenang-wenangnya, termasuk kategori yang tidak kelihatan
    • Bekerja hanya pada imej skala kelabu
  2. In a common embedding-based open-vocabulary detector, how are candidate regions matched to user-supplied labels?
    • By using only the region's average brightness
    • By comparing visual-region features with text embeddings in a compatible representation space
    • By choosing labels alphabetically without visual features
    • By restricting every model to the original COCO class list
  3. Apakah sumber pralatihan yang paling membolehkan pengesanan perbendaharaan kata terbuka?
    • Pasangan teks imej berskala besar digunakan untuk mempelajari ruang bahasa penglihatan
    • Satu set kecil kotak berlabel sempurna
    • Rakaman audio
    • Set data digit tulisan tangan
  4. What replaces fixed per-class classifier weights in a common embedding-based open-vocabulary design?
    • The camera's physical image sensor
    • The bounding-box coordinate system
    • All visual features with random file identifiers
    • Representations of the supplied text labels used for similarity-based classification
  5. Manakah antara berikut merupakan contoh model pengesanan perbendaharaan kata terbuka atau pembumian?
    • ResNet-50 sahaja
    • Membumikan DINO
    • Skrip k-means kluster biasa
    • Makro hamparan
  6. What does an open-vocabulary detector's ability to use a new text category imply?
    • It guarantees accurate detection of every nameable object
    • The category must have been absent from every pretraining image and caption
    • It can attempt localization through learned vision-language associations, with accuracy requiring evaluation
    • It needs no visual features or bounding-box output
  7. What output distinguishes text-conditioned object detection from simply saying that an image contains a named category?
    • Only a whole-image tag with no object location
    • Only the text prompt's word count
    • Only the image's dimensions and filename
    • Locations such as bounding boxes for the matching objects
  8. Before using open-vocabulary predictions to auto-label a new domain, what should a dataset team check?
    • The boxes and labels under representative prompts, thresholds, and domain conditions
    • Assume text-conditioned predictions are automatically ground truth
    • Verify only that the label strings contain no spelling errors
    • Discard all visual inspection because image-text pretraining guarantees accuracy