Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

31 Jul 2017Zhenguo LiFengwei ZhouFei ChenHang Li

Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Meta SGD Accuracy 17.56 # 2
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Matching Nets, (from ) Accuracy 17.31 # 3
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Meta LSTM, (from ) Accuracy 16.70 # 4
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) MAML, (from ) Accuracy 16.49 # 5
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Meta SGD Accuracy 28.92 # 2
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Meta LSTM, (from ) Accuracy 26.06 # 3
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Matching Nets, (from ) Accuracy 22.69 # 4
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) MAML, (from ) Accuracy 19.29 # 5

Methods used in the Paper