REVIEW 18 cited by
Bridging the Gap to Real-World 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
Bridging the Gap to Real-World Object-Centric Learning
read the original abstract
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing image-based object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real-world datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature.
Forward citations
Cited by 18 Pith papers
-
Identifying Latent Concepts and Structures for Generalized Category Discovery
CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
-
Structure over Pixels: Learning Variable-Length Visual Programs
STROP learns variable-length discrete visual programs for images by training a length head against frozen DINOv3 features in a four-phase curriculum while bypassing pixel reconstruction.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven gener...
-
TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
TSA adds learned activation scores to control slot state preservation and decoder participation in recurrent video object-centric models, improving decomposition and identity preservation on occluded videos.
-
TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
TSA learns per-slot, per-frame activation scores that gate state updates and decoder attention, preserving object identity through occlusion in unsupervised video object-centric learning.
-
Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning
DSSA decouples per-frame appearance from temporal identity in slot attention mechanisms to reduce slot swapping and improve temporal consistency in video object segmentation.
-
Formalizing the Binding Problem
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.
-
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGeo reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations across views while suppressing view-specific noise.
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
-
Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting
A scene-agnostic object codebook learned via unsupervised object-centric learning provides consistent identity-anchored representations for 3D Gaussians across multiple scenes.
-
ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks
A cycle-consistent GAN that translates between images and object lists matches state-of-the-art detection on synthetic scenes and detects low-contrast cells where slot-attention models fail.
-
Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation
Slot-based object-centric visual representations, especially with robot-video pretraining, improve out-of-distribution generalization of robotic manipulation policies compared to global and dense pre-trained features.
-
Learning Object-Centric Representations in SAR Images with Multi-Level Feature Fusion
SlotSAR fuses wavelet scattering features with a SAR foundation model's semantic features to make slot attention separate targets from clutter in SAR images, improving segmentation metrics on ATRNet-STAR.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
-
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGeo reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations while suppressing view-specific noise, outperforming prior methods on benchmarks.
-
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGeo applies an information bottleneck to object-centric learning for improved cross-view generalization in UAV geo-localization.
-
InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
InfoGeo reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations across views while minimizing view-specific noise.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.