Our new X account is live! Follow @wizwand_team for updates

Image Captioning on MS-COCO

154.9CIDEr

OFA

Updated 2d ago

Evaluation Results

Method
OFA 2023.06	154.9	-	-	26.6	-	-	-	-	-
GIT2 2023.06	152.7	-	-	26.4	-	-	-	-	-
VALOR 2023.06	152.5	-	-	25.7	-	-	-	-	-
GIT 2023.06	151.1	-	-	26.3	-	-	-	-	-
COSA 2023.06	150.6	-	-	27	-	-	-	-	-
BEiT-3 2023.06	147.6	-	-	25.4	-	-	-	-	-
BLIP-2 2023.06	145.8	-	-	-	-	-	-	-	-
CoCa 2023.06	143.6	-	-	24.7	-	-	-	-	-
SimVLM 2023.06	143.3	-	-	25.4	-	-	-	-	-
OSCARL 2020.04	140	41.7	30.6	24.5	-	-	-	-	-
Flamingo 2023.06	138.1	-	-	-	-	-	-	-	-
mPLUG-2 2023.06	137.7	-	-	23.7	-	-	-	-	-
OSCARB 2020.04	137.6	40.5	29.7	22.8	-	-	-	-	-
BLIP 2023.06	136.7	-	-	-	-	-	-	-	-
LEMON 2022.11	133.3	40.3	30.2	-	-	-	-	-	-
SoTAS 2020.04	129.8	38.9	29.2	22.4	-	-	-	-	-
SoTAB 2020.04	129.3	39.5	29.3	23.2	-	-	-	-	-
CapPa L/14 2023.06	125.8	-	-	-	-	-	-	-	-
CLIP L/14 2023.06	124.4	-	-	-	-	-	-	-	-
Oscar 2022.11	123.7	36.5	30.3	-	-	-	-	-	-
CLIP* L/14 2023.06	123.2	-	-	-	-	-	-	-	-
CLIP 2023.06	118.4	-	-	-	-	-	-	-	-
CapPa 2023.06	117.9	-	-	-	-	-	-	-	-
Cap 2023.06	117.5	-	-	-	-	-	-	-	-
UniVLP 2022.11	116.9	36.5	28.4	-	-	-	-	-	-
CLIP* (16k) 2023.06	116.3	-	-	-	-	-	-	-	-
CLIP* (8k) 2023.06	115.8	-	-	-	-	-	-	-	-
BUTD 2022.11	113.5	36.2	27	-	77.2	-	56.4	-	-
ClipCap 2022.11	113.1	33.5	27.5	-	74.7	-	-	-	-
VisInContext 2024.06	101.3	-	-	-	-	-	-	-	-
Open-Flamingo MOE 2024.06	98.2	-	-	-	-	-	-	-	-
VisInContext 2024.06	94.2	-	-	-	-	-	-	-	-
CapDec 2022.11	91.8	26.4	25.1	-	69.2	-	51.8	-	-
Open-Flamingo MOE 2024.06	90.5	-	-	-	-	-	-	-	-
VisInContext 2024.06	84.4	-	-	-	-	-	-	-	-
Open-Flamingo MOE 2024.06	82.3	-	-	-	-	-	-	-	-
Flamingo 2024.12	79.4	-	-	-	-	-	-	-	-
VisualGPT 2021.02	75.8	24.3	21.9	-	67.1	48.6	-	-	-
OpenFlamingo 2024.12	65.5	-	-	-	-	-	-	-	-
CM3Leon 2024.12	61.6	-	-	-	-	-	-	-	-
D-DiT 2024.12	56.2	-	-	-	-	-	-	-	-
Kim et al. + unpaired 2021.02	55.2	18.7	20.7	-	63	-	-	-	-
Feng et al. 2021.02	54.9	18.6	17.9	-	58.9	-	-	-	-
MAGIC 2022.11	49.3	12.9	17.4	-	56.8	-	39.9	-	-
Kim et al. 2021.02	36	13.4	15.9	-	58.1	-	-	-	-
ZeroCap 2022.11	34.5	7	15.4	-	49.8	-	31.8	-	-
Transfusion 2024.12	29	-	-	-	-	-	-	-	-
CapDec 2022.11	27.3	9.2	16.3	-	43.3	-	36.7	-	-
MAGIC 2022.11	18.3	5.2	12.5	-	41.4	-	30.7	-	-
Chameleon 2024.12	18	-	-	-	-	-	-	-	-
Gu et al. 2021.02	17.7	5.4	13.2	-	46.2	-	-	-	-
RefineCap 2021.09	1.272	37.8	28.3	0.225	80.2	-	0.58	64.5	49.9
Autoregressive Transformer 2022.08	1.18	33.9	-	-	-	-	57	-	-
Bit Diffusion 2022.08	1.15	34.7	-	-	-	-	58	-	-
Bit Diffusion 2022.08	1.15	34.4	-	-	-	-	57	-	-
Bit Diffusion 2022.08	1.13	34.5	-	-	-	-	57	-	-
Bridging 2021.09	1.066	33	26.4	-	-	-	0.586	-	-
SCN-LSTM 2021.09	1.041	33	25.7	-	72.8	-	-	56.6	43.3
Bit Diffusion 2022.08	1	31.5	-	-	-	-	55	-	-
Skeleton Key 2021.09	0.966	25.9	24.7	0.196	67.3	-	0.489	48.9	35.5
Att-CNN+LSTM 2021.09	0.94	31	26	-	74	-	-	56	42
Unified VLP 2022.06	-	36.5	-	-	-	-	-	-	-
OSCAR-B 2022.06	-	36.5	-	-	-	-	-	-	-
OSCAR-L 2022.06	-	37.4	-	-	-	-	-	-	-
UNICORN 2022.06	-	35.8	-	-	-	-	-	-	-
BLIP-B 2022.06	-	39.7	-	-	-	-	-	-	-
BLIP-L 2022.06	-	40.4	-	-	-	-	-	-	-
CLIP-VIL 2022.06	-	40.2	-	-	-	-	-	-	-
SimVLM 2022.06	-	40.6	-	-	-	-	-	-	-
OSCAR-L 2022.06	-	41.7	-	-	-	-	-	-	-
CoCa 2022.06	-	43.5	-	-	-	-	-	-	-
Uni-Perceiver-B 2022.06	-	32	-	-	-	-	-	-	-
Uni-Perceiver-B 2022.06	-	36.8	-	-	-	-	-	-	-
Uni-Perceiver-B 2022.06	-	37.3	-	-	-	-	-	-	-
Uni-Perceiver-B + Conditional MoEs 2022.06	-	33.2	-	-	-	-	-	-	-
Uni-Perceiver-B + Conditional MoEs 2022.06	-	38.6	-	-	-	-	-	-	-
Uni-Perceiver-B + Conditional MoEs 2022.06	-	39.2	-	-	-	-	-	-	-
Uni-Perceiver-L 2022.06	-	35.3	-	-	-	-	-	-	-
Uni-Perceiver-L 2022.06	-	39.3	-	-	-	-	-	-	-
Uni-Perceiver-L 2022.06	-	40.5	-	-	-	-	-	-	-
Uni-Perceiver-L + Conditional MoEs 2022.06	-	35.5	-	-	-	-	-	-	-
SemAttn 2021.09	-	30.4	24.3	-	70.9	-	-	53.7	40.2
LSTM-C 2021.09	-	-	-	-	-	-	0.23	-	-