One-Shot Unsupervised Cross-Domain Detection

05/23/2020
by   Antonio D'Innocente, et al.
3

Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. Although the topic has attracted attention recently, current approaches all rely on the ability to access a sizable amount of target data for use at training time. This is a heavy assumption, as often it is not possible to anticipate the domain where a detector will be used, nor to access it in advance for data acquisition. Consider for instance the task of monitoring image feeds from social media: as every image is created and uploaded by a different user it belongs to a different target domain that is impossible to foresee during training. This paper addresses this setting, presenting an object detection algorithm able to perform unsupervised adaption across domains by using only one target sample, seen at test time. We achieve this by introducing a multi-task architecture that one-shot adapts to any incoming sample by iteratively solving a self-supervised task on it. We further enhance this auxiliary adaptation with cross-task pseudo-labeling. A thorough benchmark analysis against the most recent cross-domain detection methods and a detailed ablation study show the advantage of our method, which sets the state-of-the-art in the defined one-shot scenario.

READ FULL TEXT

page 8

page 20

page 21

research
06/07/2021

Self-Supervision Meta-Learning for One-Shot Unsupervised Cross-Domain Detection

Deep detection models have largely demonstrated to be extremely powerful...
research
10/06/2021

Decoupled Adaptation for Cross-Domain Object Detection

Cross-domain object detection is more challenging than object classifica...
research
10/11/2022

CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection

Although few-shot object detection (FSOD) has attracted great research a...
research
03/10/2023

Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D c...
research
07/28/2021

SimROD: A Simple Adaptation Method for Robust Object Detection

This paper presents a Simple and effective unsupervised adaptation metho...
research
03/30/2022

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

We propose a test-time adaptation method for cross-domain image segmenta...
research
09/28/2021

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement

Since state-of-the-art approaches to offensive language detection rely o...

Please sign up or login with your details

Forgot password? Click here to reset