HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Visual Reasoning On Nlvr2 Test

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
CoCa87.0CoCa: Contrastive Captioners are Image-Text Foundation Models-
UNITER (Large)79.5UNITER: UNiversal Image-TExt Representation Learning-
SimVLM85.15SimVLM: Simple Visual Language Model Pretraining with Weak Supervision-
VLMo86.86VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts-
BLIP-129M83.09BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation-
X2-VLM (large)89.4X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks-
X2-VLM (base)87.0X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks-
X-VLM (base)84.76Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts-
SOHO77.32Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning-
LXMERT76.2LXMERT: Learning Cross-Modality Encoder Representations from Transformers-
ViLT-B/3276.13ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision-
ALBEF (14M)82.55Align before Fuse: Vision and Language Representation Learning with Momentum Distillation-
BEiT-392.58Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks-
XFM (base)88.4Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks-
0 of 14 row(s) selected.
Visual Reasoning On Nlvr2 Test | SOTA | HyperAI