Image Captioning On Coco

Metrics

BLEU-4

CIDEr

Results

Performance results of various models on this benchmark

			Paper Title
ExpansionNet v2	-	143.7	Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
M2 Transformer	-	131.2	Meshed-Memory Transformer for Image Captioning
IGINet	39.9	131.0	-
UNIMO-large	39.6	127.7	UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
RDN	-	125.2	Reflective Decoding Network for Image Captioning
Lyrics	-	121.1	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
Bit Diffusion (20 steps)	34.7	115	Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
Flamingo (80B; 4-shot)	-	103	Retrieval-Augmented Multimodal Language Modeling
RA-CM3 (2.7B)	-	89.1	Retrieval-Augmented Multimodal Language Modeling
Flamingo (3B; 4-shot)	-	85	Retrieval-Augmented Multimodal Language Modeling
Parti	-	83.9	Retrieval-Augmented Multimodal Language Modeling
NIC (ResNet-50, CutMix)	24.9	77.6	CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Vanilla CM3	-	71.9	Retrieval-Augmented Multimodal Language Modeling
X-LXMERT	-	55.8	Retrieval-Augmented Multimodal Language Modeling
minDALL-E	-	48	Retrieval-Augmented Multimodal Language Modeling
ruDALL-E-XL	-	38.7	Retrieval-Augmented Multimodal Language Modeling
DALL-E	-	20.2	Retrieval-Augmented Multimodal Language Modeling

0 of 17 row(s) selected.

Image Captioning On Coco

Metrics

BLEU-4

CIDEr

Results

Performance results of various models on this benchmark

			Paper Title
ExpansionNet v2	-	143.7	Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
M2 Transformer	-	131.2	Meshed-Memory Transformer for Image Captioning
IGINet	39.9	131.0	-
UNIMO-large	39.6	127.7	UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
RDN	-	125.2	Reflective Decoding Network for Image Captioning
Lyrics	-	121.1	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
Bit Diffusion (20 steps)	34.7	115	Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
Flamingo (80B; 4-shot)	-	103	Retrieval-Augmented Multimodal Language Modeling
RA-CM3 (2.7B)	-	89.1	Retrieval-Augmented Multimodal Language Modeling
Flamingo (3B; 4-shot)	-	85	Retrieval-Augmented Multimodal Language Modeling
Parti	-	83.9	Retrieval-Augmented Multimodal Language Modeling
NIC (ResNet-50, CutMix)	24.9	77.6	CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Vanilla CM3	-	71.9	Retrieval-Augmented Multimodal Language Modeling
X-LXMERT	-	55.8	Retrieval-Augmented Multimodal Language Modeling
minDALL-E	-	48	Retrieval-Augmented Multimodal Language Modeling
ruDALL-E-XL	-	38.7	Retrieval-Augmented Multimodal Language Modeling
DALL-E	-	20.2	Retrieval-Augmented Multimodal Language Modeling

0 of 17 row(s) selected.

Image Captioning On Coco | SOTA | HyperAI