paper-with-me

홈 › Papers

Can OOD Object Detectors Learn from Foundation Models?

2024-09-08 · Jiahui Liu, Xin Wen, Shizhen Zhao, Yingxian Chen, Xiaojuan Qi

Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, such as Stable Diffusion, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples, thereby enhancing OOD object detection. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models to automatically extract meaningful OOD data from text-to-image generative models. This offers the model access to open-world knowledge encapsulated within off-the-shelf foundation models. The synthetic OOD samples are then employed to augment the training of a lightweight, plug-and-play OOD detector, thus effectively optimizing the in-distribution (ID)/OOD decision boundaries. Extensive experiments across multiple benchmarks demonstrate that SyncOOD significantly outperforms existing methods, establishing new state-of-the-art performance with minimal synthetic data usage.

📄 PDF Abstract BibTeX arXiv:2409.05162

Code (1)

cvmi-lab/syncood 공식 구현 pytorch

Tasks

Objectobject-detectionObject DetectionWorld Knowledge

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Enhancing Novel Object Detection via Cooperative Foundational Models

2023-11-19 · Rohit Bharadwaj, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan

In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection a…

Novel Class DiscoveryNovel Object DetectionObjectobject-detection+2

Object Detectors in the Open Environment: Challenges, Solutions, and Outlook

2024-03-24 · Siyuan Liang, Wei Wang, Ruoyu Chen, Aishan Liu 외

With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detectors often operate in open environments, wh…

Incremental LearningObject

Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks

2023-11-08 · Quentin Bouniot

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vi…

Contrastive Learningimage-classificationImage ClassificationMeta-Learning+4

Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation

2026-04-24 · Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler, Dmytro Pavlichenko 외 arxiv

Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fully supervised training of object detectors requires time-intensive …

Object Segmentation

Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

2022-02-10 · Jung Im Choi, Qing Tian

Visual detection is a key task in autonomous driving, and it serves as a crucial foundation for self-driving planning and control. Deep neural networks have achieved promising results in various visual tasks, but they ar…

Adversarial AttackAdversarial DefenseAutonomous DrivingAutonomous Vehicles+2