Synthesized Classifiers for Zero-Shot Learning

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning... (read more)

PDF Abstract CVPR 2016 PDF CVPR 2016 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification AWA - 0-Shot Synthesised Classifier Accuracy 72.9% # 1
Few-Shot Image Classification CUB-200-2011 - 0-Shot Synthesised Classifier Top-1 Accuracy 54.7% # 2
Few-Shot Image Classification ImageNet - 0-Shot Synthesised Classifier Accuracy 1.5% # 1
Few-Shot Image Classification SUN - 0-Shot Synthesised Classifier Accuracy 62.7% # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet