Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders

• URL: http://arxiv.org/abs/2607.11196v1
• Date: Mon, 13 Jul 2026 07:47:09 GMT
• Title: Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders
• Abstract summary: Slot-RAE operates directly within the continuous semantic feature space of visual foundation models.<n>It eliminates the need for VAE bottlenecks and task-agnostic generative pre-training.<n>It delivers comparable unsupervised object discovery, higher-fidelity image reconstruction, and robust zero-shot compositionality.
• Score: 44.055446967139424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition and high-fidelity generation. Recent diffusion-based approaches have improved visual quality, but they almost universally rely on heavy, pretrained generative priors (e.g., Stable Diffusion) and external VAE latent spaces. In this paper, we propose Slot-RAE, a much simpler, fully integrated framework that operates directly within the continuous semantic feature space of visual foundation models (e.g., DINOv3). Slot-RAE employs a feature-space diffusion process using a Diffusion Transformer (DiT) decoder and a Representation Alignment (REPA) head. Unlike existing diffusion-based objectcentric methods that rely heavily on subsidized text-toimage priors, the generative core of Slot-RAE (Slot Attention and the DiT) is trained from scratch within the frozen VFM feature space. This eliminates the need for VAE bottlenecks and task-agnostic generative pre-training. Experiments on the COCO dataset demonstrate that despite its architectural simplicity, Slot-RAE achieves state-of-the-art results. It delivers comparable unsupervised object discovery, higher-fidelity image reconstruction, and robust zero-shot compositionality, all while being significantly faster and more computationally efficient than existing object-centric latent diffusion models.

Related papers

• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>We propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation [47.409626500688866]
  We present the DINO Spherical Autoencoder (DINO-SAE), a framework that bridges semantic representation and pixel-level reconstruction.<n>Our approach achieves state-of-the-art reconstruction quality, reaching 0.37 rFID and 26.2 dB PSNR, while maintaining strong semantic alignment to the pretrained VFM.
  arXiv  Detail & Related papers  (2026-01-30T12:25:34Z)
• Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders [74.72147962028265]
  Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet.<n>We investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation.
  arXiv  Detail & Related papers  (2026-01-22T18:58:16Z)
• REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion [11.138412313646995]
  We introduce REGLUE, a unified latent diffusion framework.<n>A lightweight convolutional semantic nonlinearly aggregates multi-layer VFM features into a low-dimensional, spatially structured representation.<n>On ImageNet 256x256, REGLUE consistently improves FID and convergence over SiT-B/2 and SiT-XL/2 baselines, as well as over REPA, ReDi, and REG.
  arXiv  Detail & Related papers  (2025-12-18T15:10:42Z)
• Latent Diffusion Model without Variational Autoencoder [78.34722551463223]
  SVG is a novel latent diffusion model without variational autoencoders for visual generation.<n>It constructs a feature space with clear semantic discriminability by leveraging frozen DINO features.<n>It enables accelerated diffusion training, supports few-step sampling, and improves generative quality.
  arXiv  Detail & Related papers  (2025-10-17T04:17:44Z)
• EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model [56.53617289548353]
  EchoGen is a pioneering framework that empowers Visual Auto-Regressive ( VAR) models with subject-driven generation capabilities.<n>We employ a semantic encoder to extract the subject's abstract identity, which is injected through decoupled cross-attention to guide the overall composition.<n>To the best of our knowledge, EchoGen is the first feed-forward subject-driven framework built upon VAR models.
  arXiv  Detail & Related papers  (2025-09-30T11:45:48Z)
• Kernel Space Diffusion Model for Efficient Remote Sensing Pansharpening [8.756657890124766]
  Kernel Space Diffusion Model (KSDiff) is a novel approach that leverages diffusion processes in a latent space to generate convolutional kernels enriched with global contextual information.<n> Experiments on three widely used datasets, including WorldView-3, GaoFen-2, and QuickBird, demonstrate the superior performance of KSDiff both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2025-05-25T06:25:31Z)
• Object-Centric Slot Diffusion [30.722428924152382]
  We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes. We demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders. We also conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD.
  arXiv  Detail & Related papers  (2023-03-20T02:40:16Z)
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE [51.09507030387935]
  Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution. We propose to use the contrastive learning framework that has been shown to be effective for self-supervised representation learning, as a means to resolve this problem. We show that using the contrastive learning framework to optimize the WAE loss achieves faster convergence and more stable optimization compared with existing popular algorithms for WAE.
  arXiv  Detail & Related papers  (2021-10-19T22:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.