Zero Shot Learning
Zero-Shot Learning (ZSL) refers to the model's ability to recognize certain categories that it has not encountered during the training process. Its core objective is to achieve effective classification and recognition on categories that were unknown during the supervised learning phase. In modern NLP, language models can evaluate downstream tasks without fine-tuning, significantly enhancing the model's generalization ability and application value. ZSL achieves inference on unseen categories by learning a mapping from the image feature space to the semantic space, or through nonlinear multimodal embeddings. Benchmark datasets such as aPY, AwA, and CUB have provided crucial support for ZSL research.
aPY - 0-Shot
AwA2
ZSL-KG
Caltech-101
CIFAR-10
CIFAR-100
COCO-MLT
ResNet-50
CUB-200 - 0-Shot Learning
zsl_ADA
CUB-200-2011
ZSL_TF-VAEGAN
DTD
EuroSAT
ZLaP*
FGVC-Aircraft
Flowers-102
Food-101
GDSCv2
MSDA
How2QA
SeViLA
ImageNet
ImageNet_CN
iVQA
FrozenBiLM
LSMDC
MedConceptsQA
gpt-4-0125-preview
MIT-States
CZSL
MSRVTT-QA
MSVD-QA
Oxford 102 Flower
Oxford-IIIT Pets
PASCAL Context
ZS3Net
SNIPS
Stanford Cars
SUN Attribute
SUN397
TVQA
UCF101
ZLaP*
VOC-MLT