Chrome Extension
WeChat Mini Program
Use on ChatGLM

G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection

Computing Research Repository (CoRR)(2024)

Shanghai Jiao Tong Univ | Huawei Noahs Ark Lab

Cited 0|Views46
Abstract
In this paper, we focus on a realistic yet challenging task, Single DomainGeneralization Object Detection (S-DGOD), where only one source domain's datacan be used for training object detectors, but have to generalize multipledistinct target domains. In S-DGOD, both high-capacity fitting andgeneralization abilities are needed due to the task's complexity.Differentiable Neural Architecture Search (NAS) is known for its high capacityfor complex data fitting and we propose to leverage Differentiable NAS to solveS-DGOD. However, it may confront severe over-fitting issues due to the featureimbalance phenomenon, where parameters optimized by gradient descent are biasedto learn from the easy-to-learn features, which are usually non-causal andspuriously correlated to ground truth labels, such as the features ofbackground in object detection data. Consequently, this leads to seriousperformance degradation, especially in generalizing to unseen target domainswith huge domain gaps between the source domain and target domains. To addressthis issue, we propose the Generalizable loss (G-loss), which is an OoD-awareobjective, preventing NAS from over-fitting by using gradient descent tooptimize parameters not only on a subset of easy-to-learn features but also theremaining predictive features for generalization, and the overall framework isnamed G-NAS. Experimental results on the S-DGOD urban-scene datasetsdemonstrate that the proposed G-NAS achieves SOTA performance compared tobaseline methods. Codes are available at https://github.com/wufan-cse/G-NAS.
More
Translated text
Key words
Object Detection
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一种用于单领域通用目标检测的通用神经架构搜索(G-NAS),通过解决特征不平衡现象和引入通用性损失(G-loss),在单领域数据训练的情况下泛化到多个不同目标领域,取得了顶尖性能。

方法】:利用可微分神经架构搜索(NAS)解决单领域通用目标检测任务,通过G-loss防止NAS过度拟合,优化参数以便更好地适应易学习和预测性特征。

实验】:在S-DGOD城市场景数据集上进行实验,结果表明G-NAS相较于基线方法取得了最先进的性能。