Beyond Object Recognition: A New Benchmark towards Object Concept Learning
원문 초록
Understanding objects is a central building block of artificial intelligence, especially for embodied AI. Even though object recognition excels with deep learning, current machines still struggle to learn higher-level knowledge, e.g., what attributes an object has, and what can we do with an object. In this work, we propose a challenging Object Concept Learning (OCL) task to push the envelope of object understanding. It requires machines to reason out object affordances and simultaneously give the reason: what attributes make an object possesses these affordances. To support OCL, we build a densely annotated knowledge base including extensive labels for three levels of object concept (category, attribute, affordance), and the causal relations of three levels. By analyzing the causal structure of OCL, we present a baseline, Object Concept Reasoning Network (OCRN). It leverages causal intervention and concept instantiation to infer the three levels following their causal relations. In experiments, OCRN effectively infers the object knowledge while following the causalities well. Our data and code are available at https://mvig-rhos.com/ocl.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Attribute-Based Classification for Zero-Shot Visual Object Categorization
Feature-Based Lie Group Transformer for Real-World Applications
NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-ID
Learning compact binary descriptors with unsupervised deep neural networks
Attributes Shape the Embedding Space of Face Recognition Models
Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.