Learning Fashion Compatibility from In-the-wild Images

• URL: http://arxiv.org/abs/2206.05982v1
• Date: Mon, 13 Jun 2022 09:05:25 GMT
• Title: Learning Fashion Compatibility from In-the-wild Images
• Authors: Additya Popli, Vijay Kumar, Sujit Jos and Saraansh Tandon
• Abstract summary: We propose to learn representations for compatibility prediction from in-the-wild street fashion images through self-supervised learning. Our pretext task is formulated such that the representations of different items worn by the same person are closer compared to those worn by other people. We conduct experiments on two popular fashion compatibility benchmarks - Polyvore and Polyvore-Disjoint outfits.
• Score: 6.591937706757015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Complementary fashion recommendation aims at identifying items from different categories (e.g. shirt, footwear, etc.) that "go well together" as an outfit. Most existing approaches learn representation for this task using labeled outfit datasets containing manually curated compatible item combinations. In this work, we propose to learn representations for compatibility prediction from in-the-wild street fashion images through self-supervised learning by leveraging the fact that people often wear compatible outfits. Our pretext task is formulated such that the representations of different items worn by the same person are closer compared to those worn by other people. Additionally, to reduce the domain gap between in-the-wild and catalog images during inference, we introduce an adversarial loss that minimizes the difference in feature distribution between the two domains. We conduct our experiments on two popular fashion compatibility benchmarks - Polyvore and Polyvore-Disjoint outfits, and outperform existing self-supervised approaches, particularly significant in cross-dataset setting where training and testing images are from different sources.

Related papers

• Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning [71.14084801851381]
  Change captioning aims to succinctly describe the semantic change between a pair of similar images. Most existing methods directly capture the difference between them, which risk obtaining error-prone difference features. We propose a distractors-immune representation learning network that correlates the corresponding channels of two image representations.
  arXiv  Detail & Related papers  (2024-07-16T13:00:33Z)
• Clothes-Changing Person Re-Identification with Feasibility-Aware Intermediary Matching [86.04494755636613]
  Current clothes-changing person re-identification (re-id) approaches usually perform retrieval based on clothes-irrelevant features. We propose a Feasibility-Aware Intermediary Matching (FAIM) framework to additionally utilize clothes-relevant features for retrieval. Our method outperforms state-of-the-art methods on several widely-used clothes-changing re-id benchmarks.
  arXiv  Detail & Related papers  (2024-04-15T06:58:09Z)
• Transformer-based Graph Neural Networks for Outfit Generation [22.86041284499166]
  TGNN exploits multi-headed self attention to capture relations between clothing items in a graph as a message passing step in Convolutional Graph Neural Networks. We propose a transformer-based architecture, which exploits multi-headed self attention to capture relations between clothing items in a graph as a message passing step in Convolutional Graph Neural Networks.
  arXiv  Detail & Related papers  (2023-04-17T09:18:45Z)
• VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training [18.753508811614644]
  Visual InCompatibility TransfORmer (VICTOR) is optimized for two tasks: 1) overall compatibility as regression and 2) the detection of mismatching items. We build upon the Polyvore outfit benchmark to generate partially mismatching outfits, creating a new dataset termed Polyvore-MISFITs. A series of ablation and comparative analyses show that the proposed architecture can compete and even surpass the current state-of-the-art on Polyvore datasets.
  arXiv  Detail & Related papers  (2022-07-27T11:18:55Z)
• Recommendation of Compatible Outfits Conditioned on Style [22.03522251199042]
  This work aims to generate outfits conditional on styles or themes as one would dress in real life. We use a novel style encoder network that renders outfit styles in a smooth latent space.
  arXiv  Detail & Related papers  (2022-03-30T09:23:32Z)
• Semi-Supervised Visual Representation Learning for Fashion Compatibility [17.893627646979038]
  We propose a semi-supervised learning approach to create pseudo-positive and pseudo-negative outfits on the fly during training. For each labeled outfit in a training batch, we obtain a pseudo-outfit by matching each item in the labeled outfit with unlabeled items. We conduct extensive experiments on Polyvore, Polyvore-D and our newly created large-scale Fashion Outfits datasets.
  arXiv  Detail & Related papers  (2021-09-16T15:35:38Z)
• From Culture to Clothing: Discovering the World Events Behind A Century of Fashion Images [100.20851232528925]
  We propose a data-driven approach to identify specific cultural factors affecting the clothes people wear. Our work is a first step towards a computational, scalable, and easily refreshable approach to link culture to clothing.
  arXiv  Detail & Related papers  (2021-02-02T18:58:21Z)
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification [70.16040194572406]
  Most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes. It is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
  arXiv  Detail & Related papers  (2020-08-14T03:49:14Z)
• Unsupervised Landmark Learning from Unpaired Data [117.81440795184587]
  Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses. We propose a cross-image cycle consistency framework which applies the swapping-reconstruction strategy twice to obtain the final supervision. Our proposed framework is shown to outperform strong baselines by a large margin.
  arXiv  Detail & Related papers  (2020-06-29T13:57:20Z)
• Fashion Recommendation and Compatibility Prediction Using Relational Network [18.13692056232815]
  We develop a Relation Network (RN) to develop new compatibility learning models. FashionRN learns the compatibility of an entire outfit, with an arbitrary number of items, in an arbitrary order. We evaluate our model using a large dataset of 49,740 outfits that we collected from Polyvore website.
  arXiv  Detail & Related papers  (2020-05-13T21:00:54Z)
• Learning Diverse Fashion Collocation by Neural Graph Filtering [78.9188246136867]
  We propose a novel fashion collocation framework, Neural Graph Filtering, that models a flexible set of fashion items via a graph neural network. By applying symmetric operations on the edge vectors, this framework allows varying numbers of inputs/outputs and is invariant to their ordering. We evaluate the proposed approach on three popular benchmarks, the Polyvore dataset, the Polyvore-D dataset, and our reorganized Amazon Fashion dataset.
  arXiv  Detail & Related papers  (2020-03-11T16:17:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.