ScholarGate
어시스턴트

방법 비교

선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.

약지도 학습 비전 트랜스포머×지식 증류×
분야딥러닝딥러닝
계열Machine learningMachine learning
기원 연도2021–20222015
창시자Dosovitskiy et al. (ViT); weak supervision paradigm from Zhou and othersHinton, G., Vinyals, O. & Dean, J.
유형Self-attention image model with weakly supervised trainingNeural network compression (teacher–student)
원전Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR). link ↗Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗
별칭WS-ViT, weakly supervised ViT, weak supervision with vision transformer, ViT with weak labelsBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
관련45
요약Weakly Supervised Vision Transformer (WS-ViT) trains a Vision Transformer on image data that lacks precise pixel-level annotations, instead using cheaper, noisier supervision such as image-level class tags, bounding boxes, or web-scraped text. The global self-attention mechanism of the transformer makes it especially capable of localising objects and learning discriminative features from these incomplete labels.Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.
ScholarGate데이터셋
  1. v1
  2. 2 출처
  3. PUBLISHED
  1. v1
  2. 2 출처
  3. PUBLISHED

검색으로 이동 슬라이드 다운로드

ScholarGate방법 비교: Weakly supervised vision transformer · Knowledge Distillation. 2026-06-17에 다음에서 검색함: https://scholargate.app/ko/compare