Papers with Code · CC BY-SA 4.0

COCO (Common Objects in Context)

아카이브 평가 67건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
RAT-Diffusion	FID 5.00	Data Extrapolation for Text-to-image Generation on Small Datasets 2024-10-02	코드 1
Re-Imagen (Finetuned)	FID 5.25	Re-Imagen: Retrieval-Augmented Text-to-Image Generator 2022-09-29	연결 없음
U-ViT-S/2-Deep	FID 5.48	All are Worth Words: A ViT Backbone for Diffusion Models 2022-09-25	코드 1 · 코드 2 · 코드 3
GLIGEN (fine-tuned, Detection + Caption data)	FID 5.61	GLIGEN: Open-Set Grounded Text-to-Image Generation 2023-01-17	코드 1
GLIGEN (fine-tuned, Detection data only)	FID 5.82	GLIGEN: Open-Set Grounded Text-to-Image Generation 2023-01-17	코드 1
U-ViT-S/2	FID 5.95	All are Worth Words: A ViT Backbone for Diffusion Models 2022-09-25	코드 1 · 코드 2 · 코드 3
ConPreDiff	FID 6.21 Zero shot FID 6.21	Improving Diffusion-Based Image Synthesis with Context Prediction 2024-01-04	연결 없음
TLDM	FID 6.29	Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders 2022-02-19	코드 1
GLIGEN (fine-tuned, Grounding data)	FID 6.38	GLIGEN: Open-Set Grounded Text-to-Image Generation 2023-01-17	코드 1
RAPHAEL (zero-shot)	FID 6.61	RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths 2023-05-29	코드 1
ERNIE-ViLG 2.0 (zero-shot)	FID 6.75	ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts 2022-10-27	코드 1 · 코드 2
Re-Imagen	FID 6.88	Re-Imagen: Retrieval-Augmented Text-to-Image Generator 2022-09-29	연결 없음
eDiff-I (zero-shot)	FID 6.95	eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers 2022-11-02	코드 1 · 코드 2
Swinv2-Imagen	FID 7.21 Inception score 31.46	Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation 2022-10-18	연결 없음
Imagen (zero-shot)	FID 7.27	Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding 2022-05-23	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
GigaGAN (Zero-shot, 64x64)	FID 7.28	Scaling up GANs for Text-to-Image Synthesis 2023-03-09	코드 1
StyleGAN-T (Zero-shot, 64x64)	FID 7.3	StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis 2023-01-23	코드 1
Make-a-Scene (unfiltered)	FID 11.84	Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors 2022-03-24	코드 1
Kandinsky	FID 8.03	Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion 2023-10-05	코드 1
Lafite	FID 8.12 Inception score 32.34 SOA-C 61.09	LAFITE: Towards Language-Free Training for Text-to-Image Generation 2021-11-27	코드 1 · 코드 2 · 코드 3
SiD-LSG (Data-free distillation, zero-shot FID)	FID 8.15 Zero shot FID 8.15	Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation 2024-06-03	코드 1 · 코드 2
simple diffusion (U-ViT)	FID 8.3	Simple diffusion: End-to-end diffusion for high resolution images 2023-01-26	코드 1
GigaGAN (Zero-shot, 256x256)	FID 9.09	Scaling up GANs for Text-to-Image Synthesis 2023-03-09	코드 1
XMC-GAN (256 x 256)	FID 9.3 Inception score 30.5	NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion 2021-11-24	코드 1
XMC-GAN	FID 9.33	Cross-Modal Contrastive Learning for Text-to-Image Generation 2021-01-12	코드 1
DALL-E 2	FID 10.39	Hierarchical Text-Conditional Image Generation with CLIP Latents 2022-04-13	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
Corgi-Semi	FID 10.6	Shifted Diffusion for Text-to-image Generation 2022-11-24	코드 1
Corgi	FID 10.88	Shifted Diffusion for Text-to-image Generation 2022-11-24	코드 1
TR0N (StyleGAN-XL, LAION2BCLIP, BLIP-2, zero-shot)	FID 10.9	TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation 2023-04-26	코드 1 · 코드 2
GLIDE (zero-shot)	FID 12.24	GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models 2021-12-20	코드 1 · 코드 2