# Towards Universal Object Detection by Domain Attention

arXiv: https://arxiv.org/abs/1904.04402 · HTML: https://mlsanity.com/paper/1904.04402/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 89)

- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [CLIP the Gap: A Single Domain Generalization Approach for Object Detection](https://mlsanity.com/paper/2301.05499/) (2023)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Detecting Everything in the Open World: Towards Universal Object Detection](https://mlsanity.com/paper/2303.11749/) (2023)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection](https://mlsanity.com/paper/2303.06880/) (2023)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training](https://mlsanity.com/paper/2203.13249/) (2022)
- [DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model](https://mlsanity.com/paper/2306.01736/) (2023)
- [Unsupervised Visual Attention and Invariance for Reinforcement Learning](https://mlsanity.com/paper/2104.02921/) (2021)
- [Dynamic Transfer for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.10583/) (2021)
- [GAIA: A Transfer Learning System of Object Detection that Fits Your Needs](https://mlsanity.com/paper/2106.11346/) (2021)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains](https://mlsanity.com/paper/2304.02950/) (2023)
- [Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2103.11351/) (2021)
- [On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.03154/) (2022)
- [DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets](https://mlsanity.com/paper/2311.04894/) (2023)
- [SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection](https://mlsanity.com/paper/2412.20665/) (2024)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.05499/) (2021)
- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [Visual Understanding of Complex Table Structures from Document Images](https://mlsanity.com/paper/2111.07129/) (2021)
- [Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark](https://mlsanity.com/paper/2207.11169/) (2022)
- [Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2109.08852/) (2021)
- [ScaleDet: A Scalable Multi-Dataset Object Detector](https://mlsanity.com/paper/2306.04849/) (2023)
- [GM-DF: Generalized Multi-Scenario Deepfake Detection](https://mlsanity.com/paper/2406.20078/) (2024)

## Abstract (arXiv)

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 will be released at http://www.svcl.ucsd.edu/projects/universal-detection/.