Zero-Shot Transfer Image Classification on ImageNet V2

Metric: Accuracy (Private) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

#	Model↕	Accuracy (Private)▼	Extra Data	Paper	Date↕	Code
1	BASIC (Lion)	81.2	No	-	-	-
2	LiT-22B	80.9	No	Scaling Vision Transformers to 22 Billion Parame...	2023-02-10	Code
3	CoCa	80.7	No	CoCa: Contrastive Captioners are Image-Text Foun...	2022-05-04	Code
4	BASIC	80.6	No	Combined Scaling for Zero-shot Transfer Learning	2021-11-19	-
5	LiT ViT-e	80.6	No	PaLI: A Jointly-Scaled Multilingual Language-Ima...	2022-09-14	Code
6	LiT-tuning	78.7	No	LiT: Zero-Shot Transfer with Locked-image text T...	2021-11-15	Code
7	EVA-CLIP-18B	77.9	No	EVA-CLIP-18B: Scaling CLIP to 18 Billion Paramet...	2024-02-06	Code
8	InternVL-C	77.3	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
9	EVA-CLIP-E/14+	75.7	No	EVA-CLIP: Improved Training Techniques for CLIP ...	2023-03-27	Code
10	ALIGN	70.1	No	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
11	CLIP	70.1	No	Learning Transferable Visual Models From Natural...	2021-02-26	Code
12	AltCLIP	68.1	No	AltCLIP: Altering the Language Encoder in CLIP f...	2022-11-12	Code
13	PaLI	64.46	No	PaLI: A Jointly-Scaled Multilingual Language-Ima...	2022-09-14	Code