.png){kind=icon}
.png){kind=icon}
Return
Self-supervised Structured Object Representation Learning
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-14492-8_23.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured representation in scenes. In this work, we propose a self-supervised approach that progressively builds structured visual representations by combining semantic grouping, instance level separation, and hierarchical structuring. Our approach, based on a novel ProtoScale module, captures visual elements across multiple spatial scales. Unlike common strategies like DINO that rely on random cropping and global embeddings, we preserve full scene context across augmented views to improve performance in dense prediction tasks. We validate our method on downstream object detection tasks using a combined dataset built from selected subsets of COCO and UA-DETRAC. Experimental results show that our method learns object centric representations that enhance supervised object detection and outperform the state-of-the-art methods, even when trained with limited annotated data and fewer fine-tuning epochs.
Keywords:
Self-supervised learning
Object detection
Dense prediction
Computer vision
Journal
A
IF:
0
Papers:
30
Citations:
0