SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09394 · ECCV · 2024

GiT: Towards Generalist Vision Transformer through Universal Language Interface

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

GiT: Generalist Vision Transformer to dense prediction (e.g. segmentation). Based on the above designs, the entire model is composed solely of a ViT, without any specific additions, offering a remarkable architectural simplification. GiT is a multi-task visual model, jointly trained across five representative benchmarks without task-specific fine-tuning. Interestingly, our GiT builds a new benchmark in generalist performance, and fosters mutual enhancement across tasks, leading to significant improvements compared to isolated training. This reflects a similar impact observed in LLMs. Further enriching training with 27 datasets, GiT achieves strong zero-shot results over various tasks. Due to its simple design, this paradigm holds promise for narrowing the architectural gap between vision and language. Code and models are available at https://github.com/Haiyang-W/GiT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.09394")
get_code_for_paper("2403.09394")
have("2403.09394")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.09394.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.09394.svg)](https://syntology.ai/paper/2403.09394)

Connect an agent — have() is free.