Papers with Code 아카이브

Disentanglement

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 3
보존된 평가 기록: 4

This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/TAMU-VITA/UAV-NDFT

공식 코드

Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach

https://github.com/TPCD/DG-VAE

공식 코드

Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification

https://github.com/TeddLi/Disentangle

공식 코드

DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement

https://github.com/ThomasMrY/Groupified-VAE

공식 코드

Towards Building A Group-based Unsupervised Representation Disentanglement Framework

https://github.com/Tianhao-Qi/DEADiff_code

공식 코드

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

https://github.com/TsaftarisCollaboratory/CSDisentanglement_Metrics_Library

공식 코드

Measuring the Biases and Effectiveness of Content-Style Disentanglement

https://github.com/VITA-Group/UAV-NDFT

공식 코드

Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach

https://github.com/Wendison/VQMIVC

공식 코드

VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

https://github.com/Willy1005/2025-IJCAI-RDML

공식 코드

Reliable Disentanglement Multi-view Learning Against View Adversarial Attacks

https://github.com/XLearning-SCU/2021-IJCV-YOLY

공식 코드

You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network

https://github.com/XiangZongyi/CoPD

공식 코드

Coherence-guided Preference Disentanglement for Cross-domain Recommendations

https://github.com/XiaokunSun/Barbie

공식 코드

Barbie: Text to Barbie-Style 3D Avatars

https://github.com/Xiaoming-Yu/DMIT

공식 코드

Multi-mapping Image-to-Image Translation via Learning Disentanglement

https://github.com/YadiraF/DECA

공식 코드

Learning an Animatable Detailed 3D Face Model from In-The-Wild Images

https://github.com/Yang-Liu1082/FDN

공식 코드

Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network

https://github.com/YoungSeng/SRD-VC

공식 코드

Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion

https://github.com/YuWLong666/CoE

공식 코드

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

https://github.com/YueWuHKUST/AniFaceGAN

공식 코드

AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars

https://github.com/Yuheng-Li/MixNMatch

공식 코드

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

https://github.com/ZPDu/Domain-general-Crowd-Counting-in-Unseen-Scenarios

공식 코드

Domain-General Crowd Counting in Unseen Scenarios

https://github.com/ZZWaang/polyphonic-chord-texture-disentanglement

공식 코드

Learning Interpretable Representation for Controllable Polyphonic Music Generation

https://github.com/ZejianLi/analogical-training

공식 코드

Unsupervised Disentangled Representation Learning with Analogical Relations

https://github.com/ZerojumpLine/DecGAN

공식 코드

Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition

https://github.com/Zhiyuan1991/proVLAE

공식 코드

Progressive Learning and Disentanglement of Hierarchical Representations

https://github.com/ZoneLikeWonderland/Neural-Video-Portrait-Relighting-in-Real-time-via-Consistency-Modeling

공식 코드

Neural Video Portrait Relighting in Real-time via Consistency Modeling

https://github.com/aaltoml/generative-inverse-heat-dissipation

공식 코드

Generative Modelling With Inverse Heat Dissipation

https://github.com/abbasiReza/CLIP-COoD

공식 코드

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models

https://github.com/aburns4/UnsupDisent

공식 코드

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

https://github.com/adamdad/knowledgefactor

공식 코드

Factorizing Knowledge in Neural Networks

https://github.com/agonzgarc/cross-domain-disen

공식 코드

Image-to-image translation for cross-domain disentanglement

https://github.com/ahachang/defend

공식 코드

Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement

https://github.com/ai4life-group/sae_robustness

공식 코드

Interpretability Illusions with Sparse Autoencoders: Evaluating Robustness of Concept Representations

https://github.com/aiandglobaldevelopmentlab/textdisentanglement

공식 코드

Can Large Language Models (or Humans) Disentangle Text?

https://github.com/akatigre/multi2one

공식 코드

Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance

https://github.com/akomand/causaldiffae

공식 코드

Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models

https://github.com/akomand/icm-vae

공식 코드

Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.