Provably Learning Object-Centric Representations
원문 초록
Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While recent efforts to this end have shown promising empirical progress, a theoretical account of when unsupervised object-centric representation learning is possible is still lacking. Consequently, understanding the reasons for the success of existing object-centric methods as well as designing new theoretically grounded methods remains challenging. In the present work, we analyze when object-centric representations can provably be learned without supervision. To this end, we first introduce two assumptions on the generative process for scenes comprised of several objects, which we call compositionality and irreducibility. Under this generative process, we prove that the ground-truth object representations can be identified by an invertible and compositional inference model, even in the presence of dependencies between objects. We empirically validate our results through experiments on synthetic data. Finally, we provide evidence that our theory holds predictive power for existing object-centric models by showing a close correspondence between models' compositionality and invertibility and their empirical identifiability.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Multiple Object Stitching for Unsupervised Representation Learning
Feature-Based Lie Group Transformer for Real-World Applications
Universal Fine-grained Visual Categorization by Concept Guided Learning
ERNet: Efficient and Reliable Human-Object Interaction Detection
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.