AI Paper Atlas

Research map / Video / Video segmentation and tracking

SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models

Ziyi Wu, Nikita Dvornik, Klaus Greff, Thomas Kipf, Animesh Garg

ICLR 2023 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 10 citations (OpenAlex)

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 changedWhereMeasuredEffect
Image reconstruction loss L_I added to slot dynamics training (ablation)SlotFormer (SAVi-based) · OBJ3DLPIPS: 0.093 -> 0.080Improved
Teacher forcing instead of rollout-based training with predicted slots (ablation)SlotFormer · OBJ3DLPIPS: 0.080 -> 0.106Hurt
Teacher forcing instead of rollout-based training (ablation)SlotFormer · PhysionImproved accuracy: 1.9 -> 0.2Hurt
Temporal-only positional encoding instead of naive per-slot sinusoidal encoding (ablation)SlotFormer · PhysionImproved accuracy: 1.6 -> 1.9Improved
Temporal-only positional encoding instead of naive per-slot sinusoidal encoding (ablation)SlotFormer · OBJ3DLPIPS: 0.082 vs 0.080No clear effect
Burn-in length T=3 instead of T=6 default (ablation)SlotFormer · OBJ3DPSNR: 32.40 -> 31.26Hurt
Transformer layers increased to 8 (from 4) (ablation)SlotFormer · OBJ3DLPIPS: 0.080 -> 0.087Hurt
Transformer layers increased to 4 (from 8) on Physion (ablation)SlotFormer · PhysionImproved accuracy: 1.9 -> 1.3Hurt
Autoregressive SlotFormer rollout with SlotFormer predicted future slots fed to AloeAloe on CLEVRER predictive questions · CLEVRER predictive VQAper question accuracy: 87.3 -> 93.3Improved
Unsupervised SlotFormer dynamics rollout added to planningSAVi success classifier on PHYRE · PHYRE-1B within-templateAUCCESS: 80.7 -> 82.0Improved
Object-centric slot dynamics instead of pixel-based PredRNNvideo prediction · OBJ3DLPIPS: 0.12 -> 0.08Improved
SlotFormer dynamics on slots vs VQ patch tokens (VQFormer)video prediction · CLEVRERLPIPS: 0.18 -> 0.11Improved

Later papers that compared with this method

3 later accepted papers report SlotFormer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy