Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Unified-IOXL

Unified-IOXL

Reported on 8 benchmarks across 4 tasks · 1 paper · 8 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Object LocalizationonGRIT
Localization (ablation)· 2022-06-17
67
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Object LocalizationonGRIT
Localization (test)· 2022-06-17
67.1
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Object SegmentationonGRIT
Segmentation (ablation)· 2022-06-17
56.3
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Object SegmentationonGRIT
Segmentation (test)· 2022-06-17
56.5
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Object CategorizationonGRIT
Categorization (ablation)· 2022-06-17
61.7
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Object CategorizationonGRIT
Categorization (test)· 2022-06-17
60.8
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916

Natural Language Processing2 results

Visual Question Answering (VQA)onGRIT
VQA (ablation)· 2022-06-17
74.5
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916
Visual Question Answering (VQA)onGRIT
VQA (test)· 2022-06-17
74.5
SOTA
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks arXiv:2206.08916