Image Captioning on COCO (Common Objects in Context)

17개 결과 · ⬇ CSV · JSON

CIDEr

Rank	Model	CIDEr	BLEU-1	BLEU-2	BLEU-3	BLEU-4	METEOR	ROUGE	ROUGE-L	Paper	Code	Year
1	ExpansionNet v2	143.7	–	–	–	–	–	–	–	Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning	jchenghu/expansionnet_v2	2022
2	M2 Transformer	131.2	–	–	–	–	–	–	–	Meshed-Memory Transformer for Image Captioning	aimagelab/meshed-memory-transformer · Japanese-Image-Captioning/M2-transformer-for-Japanese	2019
3	IGINet	131.0	81.1	65.9	51.7	39.9	29.4	–	59.2
4	UNIMO-large	127.7	–	–	–	39.6	–	–	–	UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning	PaddlePaddle/PaddleNLP · PaddlePaddle/Research · PaddlePaddle/Research	2020
5	RDN	125.2	–	–	–	–	–	–	–	Reflective Decoding Network for Image Captioning		2019
6	Lyrics	121.1	–	–	–	–	–	–	–	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects		2023
7	Bit Diffusion (20 steps)	115	–	–	–	34.7	–	–	58	Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning	lucidrains/imagen-pytorch · google-research/pix2seq · pinellolab/dna-diffusion · +4	2022
8	Flamingo (80B; 4-shot)	103	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
9	RA-CM3 (2.7B)	89.1	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
10	Flamingo (3B; 4-shot)	85	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
11	Parti	83.9	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
12	NIC (ResNet-50, CutMix)	77.6	64.2	46.3	33.6	24.9	23.1	49	–	CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features	rwightman/pytorch-image-models · pytorch/vision · kornia/kornia · +27	2019
13	Vanilla CM3	71.9	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
14	X-LXMERT	55.8	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
15	minDALL-E	48	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
16	ruDALL-E-XL	38.7	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022
17	DALL-E	20.2	–	–	–	–	–	–	–	Retrieval-Augmented Multimodal Language Modeling		2022