Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior
원문 초록
The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local patches of an image. The competition has a weak inductive bias to preserve spatial continuity; consequently, one slot may claim patches scattered diffusely throughout the image. In contrast, the inductive bias of human vision is strong, to the degree that attention has classically been described with a spotlight metaphor. We incorporate a spatial-locality prior into state-of-the-art object-centric vision models and obtain significant improvements in segmenting objects in both synthetic and real-world datasets. Similar to human visual attention, the combination of image content and spatial constraints yield robust unsupervised object-centric learning, including less sensitivity to model hyperparameters.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
Refine Any Object in Any Scene
토론
이 논문과 연결된 포럼 글이 아직 없습니다.