paper-with-me

홈 › Papers

Addressing the Topological Defects of Disentanglement via Distributed Operators

2021-02-10 · Diane Bouchacourt, Mark Ibrahim, Stéphane Deny

A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in learning to map each of these factors to distinct subspaces of a model's latent representation. However, this approach has shown limited empirical success to date. Here, we show that, for a broad family of transformations acting on images--encompassing simple affine transformations such as rotations and translations--this approach to disentanglement introduces topological defects (i.e. discontinuities in the encoder). Motivated by classical results from group representation theory, we study an alternative, more flexible approach to disentanglement which relies on distributed latent operators, potentially acting on the entire latent space. We theoretically and empirically demonstrate the effectiveness of this approach to disentangle affine transformations. Our work lays a theoretical foundation for the recent success of a new generation of models using distributed operators for disentanglement.

📄 PDF Abstract BibTeX arXiv:2102.05623

Code (1)

facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement 공식 구현 pytorch

Tasks

Disentanglement

Similar Papers 제목 키워드 기반

Addressing the Topological Defects of Disentanglement

2021-01-01 · Diane Bouchacourt, Mark Ibrahim, Stephane Deny

A core challenge in Machine Learning is to disentangle natural factors of variation in data (e.g. object shape vs pose). A popular approach to disentanglement consists in learning to map each of these factors to distinc…

Disentanglement

Disentanglement Learning via Topology

2023-08-24 · Nikita Balabin, Daria Voronkova, Ilya Trofimov, Evgeny Burnaev 외

We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial property of data representations substantia…

Disentanglement

Controlling Topological Defects in Polar Fluids via Reinforcement Learning

2025-07-25 · Abhinav Singh, Petros Koumoutsakos arxiv

Topological defects in active polar fluids exhibit complex dynamics driven by internally generated stresses, reflecting the deep interplay between topology, flow, and non-equilibrium hydrodynamics. Feedback control offer…

Reinforcement Learning

Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR

2019-08-23 · Nick Byrne, James R. Clough, Isra Valverde, Giovanni Montana 외

Patient-specific 3D printing of congenital heart anatomy demands an accurate segmentation of the thin tissue interfaces which characterise these diagnoses. Even when a label set has a high spatial overlap with the ground…

AnatomyData AugmentationSegmentation

ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Search

2026-01-22 · Xiangyu Wang, Zhixin Lv, Yongjiao Sun, Anrui Han 외 arxiv

Text-Based Person Search (TBPS) holds unique value in real-world surveillance bridging visual perception and language understanding, yet current paradigms utilizing pre-training models often fail to transfer effectively …

Person Search