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.
arXiv preprint arXiv:2209.14860 , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 10representative citing papers
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.
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 generalization.
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.
DSSA decouples per-frame appearance from temporal identity in slot attention mechanisms to reduce slot swapping and improve temporal consistency in video object segmentation.
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 reformulates cross-view geo-localization as an information bottleneck that aligns object-centric structural relations across views while suppressing view-specific noise.
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.
A scene-agnostic object codebook learned via unsupervised object-centric learning provides consistent identity-anchored representations for 3D Gaussians across multiple scenes.
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.
citing papers explorer
-
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 generalization.
-
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.
-
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.
-
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.