Learning the semantic structure of objects from Web supervision
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet learning large space of such concepts remains elusive due to the high cost of providing detailed object annotations for supervision. The key contribution of this paper is an algorithm to learn the nameable parts of objects automatically, from images obtained by querying Web search engines. The key challenge is the high level of noise in the annotations; to address it, we propose a new unified embedding space where the appearance and geometry of objects and their semantic parts are represented uniformly. Geometric relationships are induced in a soft manner by a rich set of nonsemantic mid-level anchors, bridging the gap between semantic and non-semantic parts. We also show that the resulting embedding provides a visually-intuitive mechanism to navigate the learned concepts and their corresponding images.
Code (0)
등록된 구현이 없습니다.
Tasks
NavigateSimilar Papers 제목 키워드 기반
Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes
The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a no…
3D Semantic SegmentationPoint Cloud SegmentationScene SegmentationSegmentation+3MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels. However, most approaches struggle to produce accura…
Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationCollaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions
Per-pixel masks of semantic objects are very useful in many applications, which, however, are tedious to be annotated. In this paper, we propose a human-agent collaborative annotation approach that can efficiently genera…
ObjectSuperpixelsTAGH2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
Hierarchical 3D grouping aims to recover scene groups across multiple granularities, from fine object parts to complete objects, without relying on semantic labels or a fixed vocabulary. The main challenge is to transfor…
Iterative Superquadric Recomposition of 3D Objects from Multiple Views
Humans are good at recomposing novel objects, i.e. they can identify commonalities between unknown objects from general structure to finer detail, an ability difficult to replicate by machines. We propose a framework, IS…
Inductive BiasObject