Kuiz berkaitan panduan · Keras Tahap

Penghafalan dalam Kuiz Model Resapan

Menguji maksud hafalan dalam model penyebaran, sebab data latihan pendua menyebabkannya, dan cara penyelidik mengekstrak dan mengurangkan salinan hampir.

Laluan panduan yang berkaitanHafalan Dalam Model Resapan
soalan 1 daripada 8

Apakah hafalan dalam model resapan?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Apakah hafalan dalam model resapan?
    • The model remembering a user's previous prompts
    • The model reproducing specific training images almost exactly
    • The model storing images in a database for search
    • The model forgetting how to draw after training
  2. Mengapakah data pendua meningkatkan hafalan?
    • Duplicates are stored in higher resolution
    • Duplicates are removed automatically before training
    • When an image appears many times, storing it becomes the easiest way to reduce training loss on it
    • Duplicates confuse the model so it outputs noise
  3. Apakah yang ditunjukkan oleh kertas kerja Carlini dan rakan sekerja 2023?
    • Diffusion models never copy training data
    • Only text models memorize data
    • Memorization only happens in black and white images
    • Over a hundred near-identical training images could be extracted from Stable Diffusion
  4. Bagaimanakah serangan pengekstrakan mengenal pasti imej yang mungkin dihafal?
    • It looked for near-identical generations across many seeds for the same caption
    • It read the model's weights directly as images
    • It asked the model which images it had memorized
    • It searched the web for similar photos
  5. Pernyataan manakah tentang hafalan yang tepat?
    • It is the model's normal behavior for every prompt
    • It is rare but can be targeted by a determined user
    • It only occurs as exact pixel copies
    • It has no relevance to privacy
  6. Why is privacy risk sharper when fine-tuning on a small dataset such as medical scans?
    • Small datasets are always public
    • Medical scans are too large to train on
    • Each example has more influence on the model, raising the chance of regurgitation
    • Fine-tuning deletes the base model
  7. Which mitigation bounds the influence of any single training example but currently reduces image quality?
    • Differentially private training
    • Increasing the number of sampling steps
    • Menggunakan gesaan yang lebih panjang
    • Training for more epochs
  8. Why is deduplication more effective when it removes near-duplicates, not only exact copies?
    • Exact copies do not affect training
    • Near-duplicates are illegal to store
    • Near-duplicates make images blurrier
    • Slightly edited versions of the same image still act as repeated exposure