Towards Universal Object Detection by Domain Attention

Abstract

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 1.3× parameter increase over a single-domain baseline detector. The code and benchmark will be released at

Deep Learning for Generic Object Detection: A Survey

“…(9) Universal Object Detection: Recently, there has been increasing effort in learning universal representations, those which are effective in multiple image domains, such as natural images, videos, aerial images, and medical CT images [224,225]. Most such research focuses on image classification, rarely targeting object detection [281], and developed detectors are usually domain specific. Object detection independent of image domain and crossdomain object detection represent important future directions.…”

Lightweight Attention Pyramid Network for Object Detection and Instance Segmentation

“…Thus, the irrelevant background boxes can be filtered out. Wang et al [34] proposed a novel domain-attention mechanism for a universal object detection model. A domain-attention module is leveraged and enables adapters to specialize on some individual domains.…”

Automated location invariant animal detection in camera trap images using publicly available data sources

“…Despite their benefits as out-of-the-box solutions, universal or general object detectors usually fail to achieve the high accuracy attainable by domain-specific object detectors (Rebuffi et al, 2017;Wang et al, 2019). Due to the need to achieve high accuracy object detection and classification in ecological research, it may therefore be necessary to optimize location invariant models for domainspecific studies.…”