SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10341 · ECCV · 2022

UFO: Unified Feature Optimization

Jian Wang, Errui Ding, Jingdong Wang, Yifan Sun, Haocheng Feng, Junyu Han, Xinyu Zhang, Zhigang Wang, Lufei Liu, Jinwen Chen, Jingtuo Liu, Teng Xi, and 4 more

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

This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under realworld and large-scale scenarios, which requires a collection of multiple AI functions. UFO aims to benefit each single task with a large-scale pretraining on all tasks. Compared with existing foundation models, UFO has two points of emphasis, i.e., relatively smaller model size and NO adaptation cost: 1) UFO squeezes a wide range of tasks into a moderatesized unified model in a multi-task learning manner and further trims the model size when transferred to down-stream tasks. 2) UFO does not emphasize transfer to novel tasks. Instead, it aims to make the trimmed model dedicated for one or more already-seen task. To this end, it directly selects partial modules in the unified model, requiring completely NO adaptation cost. With these two characteristics, UFO provides great convenience for flexible deployment, while maintaining the benefits of large-scale pretraining. A key merit of UFO is that the trimming process not only reduces the model size and inference consumption, but also even improves the accuracy on certain tasks. Specifically, UFO considers the multi-task training and brings a two-fold impact on the unified model: some closely-related tasks have mutual benefits, while some tasks have conflicts against each other. UFO manages to reduce the conflicts and preserve the mutual benefits through a novel Network Architecture Search (NAS) method. Experiments on a wide range of deep representation learning tasks (i.e., face recognition, person re-identification, vehicle re-identification and product retrieval) show that the model trimmed from UFO achieves higher accuracy than its single-task-trained counterpart and yet has smaller model size, validating the concept of UFO. Besides, UFO also supported the release of 17 billion parameters computer vision (CV) foundation model which is the largest CV model in the industry.

For agents

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

get_harvested_code_for_paper("2207.10341")
get_code_for_paper("2207.10341")
have("2207.10341")

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

curl https://syntology.ai/api/ran/2207.10341.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.10341.svg)](https://syntology.ai/paper/2207.10341)

Connect an agent — have() is free.