Visual Self-supervised Learning Scheme for Dense Prediction Tasks on X-ray Images
원문 초록
Recently, significant advancements in artificial intelligence have been attributed to the integration of self-supervised learning (SSL) scheme. While SSL has shown impressive achievements in natural language processing (NLP), its progress in computer vision has comparatively lagged behind. However, the incorporation of contrastive learning into existing visual SSL models has led to considerable progress, often surpassing supervised counterparts. Nonetheless, these improvements have been mostly limited to classification tasks. Moreover, few studies have evaluated visual SSL models in real-world scenarios, as most have focused on datasets with class-wise portrait images, notably ImageNet. Here, we focus on dense prediction tasks using security inspection x-ray images to evaluate our proposed model, Segment Localization (SegLoc). Based upon the Instance Localization (InsLoc) model, SegLoc addresses one of the key challenges of contrastive learning, i.e., false negative pairs of query embeddings. Our pre-training dataset is synthesized by cutting, transforming, and pasting labeled segments from an existing labeled dataset (PIDray) as foregrounds onto instances from an unlabeled dataset (SIXray) as backgrounds. Furthermore, we fully leverage the labeled data by incorporating the concept, one queue per class, into the MoCo-v2 memory bank, thereby avoiding false negative pairs. In our experiments, SegLoc outperformed random initialization by 3% to 6% while underperformed supervised initialization, in terms of AR and AP metrics across different IoU values over 20 to 30 pre-training epochs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
SSAVSV: Towards Unified Model for Self-Supervised Audio-Visual Speaker Verification
T3RD: Test-Time Training for Rumor Detection on Social Media
토론
이 논문과 연결된 포럼 글이 아직 없습니다.