mlsanityData to 7 Oct 2026

Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation

arXiv 2004.06229 ↗First posted 13 Apr 2020cs.LG cs.CVcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Fashion is a complex social phenomenon. People follow fashion styles from demonstrations by experts or fashion icons. However, for machine agent, learning to imitate fashion experts from demonstrations can be challenging, especially for complex styles in environments with high-dimensional, multimodal observations. Most existing research regarding fashion outfit composition utilizes supervised learning methods to mimic the behaviors of style icons. These methods suffer from distribution shift: because the agent greedily imitates some given outfit demonstrations, it can drift away from one style to another styles given subtle differences. In this work, we propose an adversarial inverse reinforcement learning formulation to recover reward functions based on hierarchical multimodal representation (HM-AIRL) during the imitation process. The hierarchical joint representation can more comprehensively model the expert composited outfit demonstrations to recover the reward function. We demonstrate that the proposed HM-AIRL model is able to recover reward functions that are robust to changes in multimodal observations, enabling us to learn policies under significant variation between different styles.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 49 references that are in the map. First posted on arXiv 13 Apr 2020.

Builds on

19 of 49 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  5. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  6. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  7. 2018Multimodal Generative Models for Scalable Weakly-Supervised Learningcited by 200
  8. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
  9. 2017Learning Fashion Compatibility with Bidirectional LSTMscited by 69
  10. 2014Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictionscited by 66
  11. 2019POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashioncited by 63
  12. 2015Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrencescited by 33
7 more
  1. 2017Fashion Forward: Forecasting Visual Style in Fashioncited by 24
  2. 2017Creating Capsule Wardrobes from Fashion Imagescited by 24
  3. 2017Learning the Latent "Look": Unsupervised Discovery of a Style-Coherent Embedding from Fashion Imagescited by 19
  4. 2016Multi-Task Curriculum Transfer Deep Learning of Clothing Attributescited by 18
  5. 2016Mining Fashion Outfit Composition Using An End-to-End Deep Learning Approach on Set Datacited by 16
  6. 2017Compatibility Family Learning for Item Recommendation and Generationcited by 9
  7. 2016Automatic Attribute Discovery with Neural Activationscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion
  2. 2024Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing
  3. 2023Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing
  4. 2025Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation
  5. 2026VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis
  6. 2024RILe: Reinforced Imitation Learning
  7. 2022Diverse Imitation Learning via Self-Organizing Generative Models
  8. 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learning