mlsanityData to 7 Oct 2026

Reconstruction Bottlenecks in Object-Centric Generative Models

arXiv 2007.06245 ↗First posted 13 Jul 2020cs.LG stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of "reconstruction bottlenecks" for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 5; 2023: 6; 2024: 3.

17 papers.

Sort:

  1. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  2. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  3. 2023Provably Learning Object-Centric Representationscited by 45
  4. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
  5. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 35
  6. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  7. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16
  8. 2022Inductive Biases for Object-Centric Representations in the Presence of Complex Texturescited by 13
  9. 2022Test-time Adaptation with Slot-Centric Modelscited by 9
  10. 2023Benchmarks for Physical Reasoning AIcited by 8
  11. 2024Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policiescited by 6
  12. 2023Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Groupingcited by 4
5 more
  1. 2022ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3Dcited by 2
  2. 2021Object Pursuit: Building a Space of Objects via Discriminative Weight Generationcited by 1
  3. 2023Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learningcited by 1
  4. 2024Simplified priors for Object-Centric Learningcited by 1
  5. 2023Variational Inference for Scalable 3D Object-centric Learningcited by 0