Learning Explicit Object-Centric Representations with Vision Transformers
원문 초록
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images. In this paper, we build on the self-supervision task of masked autoencoding and explore its effectiveness for explicitly learning object-centric representations with transformers. To this end, we design an object-centric autoencoder using transformers only and train it end-to-end to reconstruct full images from unmasked patches. We show that the model efficiently learns to decompose simple scenes as measured by segmentation metrics on several multi-object benchmarks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval
FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.