Quiz collegato alla guida · Medio Livello

Twitter's Image Cropping Bias Case Quiz

Covers the saliency pipeline, Twitter’s paired-image audit percentages, limits of the “male gaze” sample and the full-image preview change.

Domanda 1 di 8

Quali dati, secondo Twitter, hanno addestrato il suo modello di salienza di ritaglio delle immagini?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. Quali dati, secondo Twitter, hanno addestrato il suo modello di salienza di ritaglio delle immagini?
    • License-plate records
    • Human eye-tracking data
    • Credit applications
    • Facial-recognition identity labels
  2. In che modo il modello di salienza ha posizionato un ritaglio di anteprima?
    • It detected the author’s race and cropped to that label
    • It chose a random square
    • It always centered on the image midpoint
    • It centered the crop on the image point with the highest predicted saliency score
  3. Nell’audit delle immagini accoppiate di Twitter del 2021, qual è stata la differenza segnalata rispetto alla parità per gli individui neri rispetto a quelli bianchi?
    • 4% in favor of white individuals
    • 50% in favor of every image
    • 4% in favor of Black individuals
    • No comparison was performed
  4. Cosa ha riportato Twitter nel suo test separato sullo “sguardo maschile”?
    • It tested millions of uploaded images
    • Every woman’s image was cropped to her legs
    • About three per 100 images in each group cropped away from the head, with no significant objectification bias found in that sample
    • The model always selected the face
  5. Quale modifica al prodotto ha dichiarato Twitter di aver apportato dopo la valutazione?
    • It stopped accepting photographs
    • It began labeling the race of each person
    • It removed all image alt text
    • It rolled out full-image previews for standard aspect-ratio photos instead of saliency crops
  6. Why is it inaccurate to say the model was trained to recognize race?
    • It was a criminal face-search model
    • It predicted salient image regions; demographic comparisons were a separate audit test
    • It had a race category as its only output
    • It was trained only on passport photos
  7. What did the audit’s 8% difference refer to?
    • Eight percent of all platform users were women
    • The rate of false racial classification
    • A paired-image comparison from parity favoring women over men
    • A reduction in image uploads
  8. Which limitation should accompany the 2021 audit percentages?
    • They reflect specified paired-image and small-sample tests, not every image or all user experiences
    • They measure the prevalence of each group on Twitter
    • They are proof that every preview was biased
    • They establish that no other harms were possible