The reviewed record of science sign in
Pith

arxiv: 2303.10834 · v5 · pith:U3ARZVUR · submitted 2023-03-20 · cs.CV · cs.LG

Object-Centric Slot Diffusion

Jindong Jiang , Fei Deng , Gautam Singh , Sungjin Ahn This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:U3ARZVURrecord.jsonopen to challenge →

classification cs.CV cs.LG
keywords diffusionobject-centricimagelearningmodelmodelsfirstgeneration
0
0 comments X
read the original abstract

The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in image generation, their integration into object-centric learning remains largely unexplored in this domain. In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach. We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes: it is the first object-centric learning model to replace conventional slot decoders with a latent diffusion model conditioned on object slots, and it is also the first unsupervised compositional conditional diffusion model that operates without the need for supervised annotations like text. Through experiments on various object-centric tasks, including the first application of the FFHQ dataset in this field, we demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders, particularly in more complex scenes, and exhibits superior unsupervised compositional generation quality. In addition, we conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD and demonstrate its effectiveness in real-world image segmentation and generation. Project page is available at https://latentslotdiffusion.github.io

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization

    cs.CV 2026-05 unverdicted novelty 7.0

    The What-Where Transformer achieves explicit what-where separation in a ViT-style backbone via concurrent token and attention-map streams, yielding emergent object discovery from attention maps and better weakly-super...

  2. Steering Optimisation Trajectories in Diffusion Representation Learning

    cs.CV 2026-07 conditional novelty 6.0

    SteeringDRL identifies two optimization regimes in diffusion autoencoders and uses gated residual U-Nets with a log SNR curriculum to steer training toward disentangled representations, improving performance across mu...

  3. Formalizing the Binding Problem

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces an information-theoretic formalization of the binding problem and a probing method to quantify binding information in deep learning model representations, tested on ViTs across challenging datasets.

  4. Deep sprite-based image models: An analysis

    cs.CV 2026-04 unverdicted novelty 6.0

    A deep sprite-based image decomposition method matches SOTA unsupervised class-aware segmentation on CLEVR, scales linearly with objects, explicitly identifies categories, and fully models images interpretably.

  5. Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM

    cs.CV 2025-05 unverdicted novelty 6.0

    Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.