Unsupervised learning based object detection using Contrastive Learning
CoRR(2024)
摘要
Training image-based object detectors presents formidable challenges, as it
entails not only the complexities of object detection but also the added
intricacies of precisely localizing objects within potentially diverse and
noisy environments. However, the collection of imagery itself can often be
straightforward; for instance, cameras mounted in vehicles can effortlessly
capture vast amounts of data in various real-world scenarios. In light of this,
we introduce a groundbreaking method for training single-stage object detectors
through unsupervised/self-supervised learning.
Our state-of-the-art approach has the potential to revolutionize the labeling
process, substantially reducing the time and cost associated with manual
annotation. Furthermore, it paves the way for previously unattainable research
opportunities, particularly for large, diverse, and challenging datasets
lacking extensive labels.
In contrast to prevalent unsupervised learning methods that primarily target
classification tasks, our approach takes on the unique challenge of object
detection. We pioneer the concept of intra-image contrastive learning alongside
inter-image counterparts, enabling the acquisition of crucial location
information essential for object detection. The method adeptly learns and
represents this location information, yielding informative heatmaps. Our
results showcase an outstanding accuracy of 89.2%, marking a
significant breakthrough of approximately 15x over random
initialization in the realm of unsupervised object detection within the field
of computer vision.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要