Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
arxiv(2023)
摘要
Traditionally, training neural networks to perform semantic segmentation
required expensive human-made annotations. But more recently, advances in the
field of unsupervised learning have made significant progress on this issue and
towards closing the gap to supervised algorithms. To achieve this, semantic
knowledge is distilled by learning to correlate randomly sampled features from
images across an entire dataset. In this work, we build upon these advances by
incorporating information about the structure of the scene into the training
process through the use of depth information. We achieve this by (1) learning
depth-feature correlation by spatially correlate the feature maps with the
depth maps to induce knowledge about the structure of the scene and (2)
implementing farthest-point sampling to more effectively select relevant
features by utilizing 3D sampling techniques on depth information of the scene.
Finally, we demonstrate the effectiveness of our technical contributions
through extensive experimentation and present significant improvements in
performance across multiple benchmark datasets.
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