REVIEW 3 cited by
GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets, which contain multiple objects of complex textures and shapes in natural everyday scenes. To address this, we introduce Guided Latent Slot Diffusion (GLASS), a novel slot-attention model that learns in the space of generated images and uses semantic and instance guidance modules to learn better slot embeddings for various downstream tasks. Our experiments show that GLASS surpasses state-of-the-art slot-attention methods by a wide margin on tasks such as (zero-shot) object discovery and conditional image generation for real-world scenes. Moreover, GLASS enables the first application of slot attention to the compositional generation of complex, realistic scenes.
Forward citations
Cited by 3 Pith papers
-
Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery
MR-DINOSAUR refines the pre-trained DINOSAUR model with pseudo-labels derived from unsupervised optical flow on quasi-static video frames to achieve state-of-the-art unsupervised multi-object discovery on TRI-PD and KITTI.
-
Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
An object-centric model that conditions a frozen pretrained diffusion model via slot adapters and an attention-alignment loss, improving unsupervised segmentation and enabling slot-based compositional image editing on COCO.
-
STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation
STORM uses a two-stage, text-guided slot attention module on frozen DINOv2 features to improve robot manipulation success and generalization to visual distractors in simulated benchmarks.
Discussion (0). Continue with ORCID to comment.