Research map / Detection and segmentation / Open-set and few-shot detection
Slot-VAE: Object-Centric Scene Generation with Slot Attention
Yanbo Wang, Letao Liu, Justin Dauwels
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the hierarchical Slot-VAE instead of slot-representation baselines | Slot-VAE · ObjectsRoom | FID: 48.4 -> 34.9 | Improved |
| use the hierarchical Slot-VAE instead of slot-representation baselines | Slot-VAE · ShapeStacks | FID: 70.4 -> 50.0 | Improved |
| use the hierarchical Slot-VAE instead of slot-representation baselines | Slot-VAE · Arrow Room | S-Acc: 0.18 -> 0.94 | Improved |
| use the hierarchical Slot-VAE instead of slot-representation baselines | Slot-VAE · ObjectsRoom | ARI-FG: 0.83 -> 0.79 | Mixed |
| add slot attention to generate slots from the global representation (ablation) | Slot-VAE · Arrow Room | FID: 289±9 -> 60.3±1 | Improved |
| add slot attention to generate slots from the global representation (ablation) | Slot-VAE · Arrow Room | S-Acc: 0.00 -> 0.94 | Improved |
| use slot attention rather than a transformer to generate slots (ablation) | Slot-VAE · Arrow Room | FID: 182.1±3 -> 60.3±1 | Improved |
| add slot attention weight sharing between the inference and generation modules (ablation) | Slot-VAE · Arrow Room | FID: 215.5±2 -> 60.3±1 | Improved |
| add slot attention weight sharing between the inference and generation modules (ablation) | Slot-VAE · Arrow Room | S-Acc: 0.00 -> 0.94 | Improved |
| share slot initialization values between the inference and generation modules (ablation) | Slot-VAE · Arrow Room | FID: 142.1±3 -> 60.3±1 | Improved |
| share slot initialization values between the inference and generation modules (ablation) | Slot-VAE · Arrow Room | S-Acc: 0.05 -> 0.94 | Improved |
Later papers that compared with this method
1 later accepted paper reports SlotVAE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Grounded Object-Centric Learning (ICLR 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GENESIS-V2 — GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement (NeurIPS 2021) · better on 4 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation (ICLR 2025 · similarity 0.90)
- Grounded Object-Centric Learning (ICLR 2024 · similarity 0.90)
- GLASS: Guided Latent Slot Diffusion for Object-Centric Learning (CVPR 2025 · similarity 0.89)
- Adaptive Slot Attention: Object Discovery with Dynamic Slot Number (CVPR 2024 · similarity 0.88)
- Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention (NeurIPS 2024 · similarity 0.87)
- MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
