Image Captioning On Nocaps In Domain

Métriques

CIDEr

METEOR

ROUGE-L

SPICE

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	B1	B2	B3	B4	CIDEr	METEOR	ROUGE-L	SPICE
git-a-generative-image-to-text-transformer	88.86	75.86	59.94	41.1	124.18	33.83	63.82	16.36
Modèle 2	84.03	69.12	51.16	33.15	100.03	30.06	59.67	14.08
Modèle 3	87.27	74.29	58.01	39.24	117.9	33.01	63.12	15.49
Modèle 4	75.31	56.79	37.85	21.91	73.73	26.02	52.44	12.04
Modèle 5	84.4	69.8	51.89	32.86	102.64	30.43	60.07	14.47
pali-a-jointly-scaled-multilingual-language	-	-	-	-	149.1	-	-	-
Modèle 7	81.61	63.74	43.22	24.82	84.79	27.27	55.03	12.3
Modèle 8	79.58	63.09	43.92	26.07	87.86	27.97	55.88	12.6
Modèle 9	72.24	51.88	29.57	14.54	58.93	22.04	49.05	8.91
Modèle 10	81.64	63.79	43.43	25.15	85.81	27.25	55.06	12.35
Modèle 11	82.91	68.02	50.75	33.59	104.25	31.33	59.67	14.85
git-a-generative-image-to-text-transformer	88.55	76.1	60.53	41.65	122.4	33.41	64.02	16.18
Modèle 13	76.48	58.76	39.28	21.96	69.59	25.08	53.22	10.94
Modèle 14	77.68	60.34	41.5	24.57	74.27	26.04	54.42	11.47
Modèle 15	82.9	68.09	49.73	31.24	96.63	29.37	58.62	13.61
simvlm-simple-visual-language-model	84.64	70.0	52.96	34.66	108.98	31.97	61.01	14.6
Modèle 17	72.76	53.52	34.13	19.45	64.37	23.47	50.53	10.11
Modèle 18	78.73	61.63	42.35	25.94	80.19	27.25	55.25	12.38
Modèle 19	76.89	57.3	37.78	21.49	80.61	28.53	53.47	14.99
grit-faster-and-better-image-captioning	-	-	-	-	105.9	-	-	13.6
Modèle 21	83.77	68.7	51.26	32.76	101.69	30.51	59.75	14.99
Modèle 22	80.7	63.27	42.86	25.78	84.83	27.23	55.91	12.06
Modèle 23	77.06	59.97	40.54	23.8	68.98	25.06	53.49	10.55
Modèle 24	74.35	55.97	36.12	20.84	70.33	25.1	52.26	11.07
Modèle 25	75.91	56.78	35.58	17.39	60.89	23.8	51.42	9.81
Modèle 26	76.49	56.2	33.73	15.14	62.96	23.68	50.84	10.13
vivo-surpassing-human-performance-in-novel	86.33	72.83	55.94	37.97	112.82	32.7	62.48	15.22
clipcap-clip-prefix-for-image-captioning	-	-	-	-	84.85	-	-	12.14
Modèle 29	77.68	60.34	41.5	24.57	74.27	26.04	54.42	11.46
vinvl-making-visual-representations-matter-in	83.24	68.04	49.68	30.62	97.99	29.51	58.54	13.63
Modèle 31	76.12	57.98	38.44	21.92	67.91	25.07	52.53	10.87
Modèle 32	77.65	59.58	39.86	22.83	76.02	26.35	53.98	11.8
Modèle 33	72.05	52.89	31.92	16.71	53.34	22.04	49.64	9.16
clipcap-clip-prefix-for-image-captioning	-	-	-	-	79.73	-	-	12.2
Modèle 35	80.5	64.48	46.46	29.59	88.08	28.7	56.84	13.04
Modèle 36	84.2	69.57	52.56	34.8	104.9	31.77	60.52	15.04
Modèle 37	80.26	63.94	44.65	27.23	87.21	27.7	56.4	12.28
Modèle 38	81.64	63.79	43.43	25.15	85.81	27.25	55.06	12.35
pali-a-jointly-scaled-multilingual-language	88.02	75.21	59.38	41.16	121.09	34.22	64.39	15.69
Modèle 40	80.68	64.7	45.33	27.09	87.28	27.7	56.76	12.79
Modèle 41	81.86	67.2	50.5	34.11	99.9	31.61	59.54	15.17