Simple multi-dataset detection

02/25/2021
by   Xingyi Zhou, et al.
14

How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for training a unified detector on multiple large-scale datasets. We use dataset-specific training protocols and losses, but share a common detection architecture with dataset-specific outputs. We show how to automatically integrate these dataset-specific outputs into a common semantic taxonomy. In contrast to prior work, our approach does not require manual taxonomy reconciliation. Our multi-dataset detector performs as well as dataset-specific models on each training domain, but generalizes much better to new unseen domains. Entries based on the presented methodology ranked first in the object detection and instance segmentation tracks of the ECCV 2020 Robust Vision Challenge.

READ FULL TEXT

page 1

page 4

page 6

research
08/22/2018

Multidomain Document Layout Understanding using Few Shot Object Detection

We try to address the problem of document layout understanding using a s...
research
03/13/2023

Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection

Current 3D object detection models follow a single dataset-specific trai...
research
01/26/2023

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupe...
research
02/27/2023

LMSeg: Language-guided Multi-dataset Segmentation

It's a meaningful and attractive topic to build a general and inclusive ...
research
03/24/2022

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

Multiple datasets and open challenges for object detection have been int...
research
12/19/2022

Million-scale Object Detection with Large Vision Model

Over the past few years, developing a broad, universal, and general-purp...
research
06/07/2022

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Leveraging large-scale data can introduce performance gains on many comp...

Please sign up or login with your details

Forgot password? Click here to reset