Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection

Zhang, Haozhuo; Yu, Huimin; Yan, Yuming; Wang, Runfa

doi:10.48550/arxiv.2203.11432

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study that demonstrated the work of Zhang et al, 22 the authors introduced an architecture aimed at disentangling features common across multiple training domains from those specific to each domain. To improve performance, only the features shared across domains were used for task solving.…”

Section: Previous Workmentioning

confidence: 99%

Domain shared features for visual inspection of complex mechanical assemblies based on synthetically generated data

Došljak,

Jovančević,

Orteu

2024

J. Electron. Imag.

View full text Add to dashboard Cite

Even though neural network methodologies have been established for a long time, only recently have they achieved exceptional efficacy in practical deployments, predominantly due to improvements in hardware computational capacity and the large amounts of available data for learning. Nonetheless, substantial challenges remain in utilizing deep learning in many domains, mainly because of the lack of large amounts of labeled data that are versatile enough for deep learning models to learn useful information. For instance, in mechanical assembly inspection, annotating data for each type of mechanical part to train a deep learning model can be very labor-intensive. Additionally, it is required to annotate data after each modification of mechanical part specification. Also, the system for inspection is typically not available until the first few samples are built to collect data. This paper proposes a solution for these challenges in case of the visual mechanical assembly inspection by processing point cloud data acquired via a three-dimensional (3D) scanner. To reduce the necessity for manually labeling large amounts of data, we employed synthetically generated data for both training and validation purposes, reserving the real sensor data exclusively for the testing phase. Our approach reduces the need for large amounts of labeled data by using synthetically generated point clouds from computer-aided design models for neural network training. Domain gap is a significant challenge for the usage of synthetically generated data. To reduce the domain gap, we used different preprocessing techniques, as well as a neural network architecture that focuses more on shared features that will not significantly change between synthetically generated data and real data from the 3D sensor.

show abstract

Section: Previous Workmentioning

confidence: 99%

Domain shared features for visual inspection of complex mechanical assemblies based on synthetically generated data

Došljak,

Jovančević,

Orteu

2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…For instance, (Volpi et al 2018;Yang et al 2021) augment the training data with adversarially perturbed samples. Other methods focus on learning domain-invariant knowledge from the source domain (Matsuura and Harada 2020;Lin et al 2021;Zhang et al 2022). Metalearning has also been popularly used to solve DG.…”

Section: Domain Generalizationmentioning

confidence: 99%

Domain-General Crowd Counting in Unseen Scenarios

Deng

Shi

2023

AAAI

View full text Add to dashboard Cite

Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain data to adapt (e.g. finetune) their models to the specific domain. In this paper, we instead target to train a model based on a single source domain which can generalize well on any unseen domain. This falls into the realm of domain generalization that remains unexplored in crowd counting. We first introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains such that we can initiate a meta-learning framework for domain generalization. The sub-domain division is dynamically refined during the meta-learning. Next, in order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules to re-encode image features. Two types of losses, i.e. feature reconstruction and orthogonal losses, are devised to enable this disentanglement. Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method. Our code is available at: https://github.com/ZPDu/Domain-general-Crowd-Counting-in-Unseen-Scenarios

show abstract

Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection

Cited by 2 publications

References 0 publications

Domain shared features for visual inspection of complex mechanical assemblies based on synthetically generated data

Domain shared features for visual inspection of complex mechanical assemblies based on synthetically generated data

Domain-General Crowd Counting in Unseen Scenarios

Contact Info

Product

Resources

About