Towards Universal Object Detection by Domain Attention

By Xudong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos. 2019

218 citations recorded by the source corpus.

Despite increasing efforts on universal representations for visual recognition, few have addressed object detection. In this paper, we develop an effective and efficient universal object detection system that is capable of working on various image domains, from human faces and traffic signs to medical CT images. Unlike multi-domain models, this universal model does not require prior knowledge of the domain of interest. This is achieved by the introduction of a new family of adaptation layers, based on the principles of squeeze and excitation, and a new domain-attention mechanism. In the proposed universal detector, all parameters and computations are shared across domains, and a single network processes all domains all the time. Experiments, on a newly established universal object detection benchmark of 11 diverse datasets, show that the proposed detector outperforms a bank of individual detectors, a multi-domain detector, and a baseline universal detector, with a 1.3x parameter increase over a single-domain baseline detector. The code and benchmark are available at http://www.svcl.ucsd.edu/projects/universal-detection/.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, methodology): “For the OD problem, COCO [50] and LVIS [29] represent two well established datasets to compare various OD methods in a single domain, while UODB [86] is a multi-domain OD benchmark.”
MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data (2020, background): “In nature image processing community, the multi-site learning is also related to multi-domain learning [4], [23], which aims to develop a single network that could perform well on diverse visual domains, achieving higher parameters efﬁciency across tasks.”
Simple Multi-dataset Detection (2021, methodology): “[40] and MSeg [19] observe a performance drop in a single unified model.”
A Survey of Deep Learning-Based Object Detection (2019, background): “[273] release a newly established universal object detection benchmark consisting of 11 diverse datasets to better meet the challenges of generalization in different domains.”
DIANet: Dense-and-Implicit Attention Network (2019, methodology): “Prior works (Wang et al. 2018; Cao et al. 2019; Hu, Shen, and Sun 2018; Hu et al. 2018; Park et al. 2018; Woo et al. 2018; Wang et al. 2019) usually insert an attention module in each layer individually.”
Continual Universal Object Detection (2020, unknown): “For Joint, we follow [35] to train a universal detector.”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “These experiments verify the large differences in object detector design between natural and aerial images and provide materials for universal object detection algorithms [30].”
Deep Learning for Generic Object Detection: A Survey (2018, background): “Most such research focuses on image classification, rarely targeting object detection (Wang et al. 2019), and developed detectors are usually domain specific.”