GAIA: A Transfer Learning System of Object Detection that Fits Your Needs

06/21/2021
by   Xingyuan Bu, et al.
0

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have distinctive demands such as certain latency constraints and specialized data distributions, it is prohibitively expensive to take advantage of large-scale pre-training for per-task requirements. In this paper, we focus on the area of object detection and present a transfer learning system named GAIA, which could automatically and efficiently give birth to customized solutions according to heterogeneous downstream needs. GAIA is capable of providing powerful pre-trained weights, selecting models that conform to downstream demands such as latency constraints and specified data domains, and collecting relevant data for practitioners who have very few datapoints for their tasks. With GAIA, we achieve promising results on COCO, Objects365, Open Images, Caltech, CityPersons, and UODB which is a collection of datasets including KITTI, VOC, WiderFace, DOTA, Clipart, Comic, and more. Taking COCO as an example, GAIA is able to efficiently produce models covering a wide range of latency from 16ms to 53ms, and yields AP from 38.2 to 46.5 without whistles and bells. To benefit every practitioner in the community of object detection, GAIA is released at https://github.com/GAIA-vision.

READ FULL TEXT

page 12

page 13

research
03/17/2022

DATA: Domain-Aware and Task-Aware Pre-training

The paradigm of training models on massive data without label through se...
research
07/23/2020

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

In natural language processing (NLP), enormous pre-trained models like B...
research
11/22/2021

Benchmarking Detection Transfer Learning with Vision Transformers

Object detection is a central downstream task used to test if pre-traine...
research
12/07/2021

Grounded Language-Image Pre-training

This paper presents a grounded language-image pre-training (GLIP) model ...
research
07/17/2020

2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge

In this report, we descibe our approach to the ECCV 2020 VIPriors Object...
research
09/10/2022

OmDet: Language-Aware Object Detection with Large-scale Vision-Language Multi-dataset Pre-training

Advancing object detection to open-vocabulary and few-shot transfer has ...
research
08/18/2023

Improving Buoy Detection with Deep Transfer Learning for Mussel Farm Automation

The aquaculture sector in New Zealand is experiencing rapid expansion, w...

Please sign up or login with your details

Forgot password? Click here to reset