Hard-Aware Fashion Attribute Classification

07/25/2019
by   Yun Ye, et al.
3

Fashion attribute classification is of great importance to many high-level tasks such as fashion item search, fashion trend analysis, fashion recommendation, etc. The task is challenging due to the extremely imbalanced data distribution, particularly the attributes with only a few positive samples. In this paper, we introduce a hard-aware pipeline to make full use of "hard" samples/attributes. We first propose Hard-Aware BackPropagation (HABP) to efficiently and adaptively focus on training "hard" data. Then for the identified hard labels, we propose to synthesize more complementary samples for training. To stabilize training, we extend semi-supervised GAN by directly deactivating outputs for synthetic complementary samples (Deact). In general, our method is more effective in addressing "hard" cases. HABP weights more on "hard" samples. For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance. Our method is verified on large scale fashion dataset, outperforming other state-of-the-art without any additional supervisions.

READ FULL TEXT

page 2

page 11

research
04/16/2019

Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN

In this paper, we introduce attribute-aware fashion-editing, a novel tas...
research
07/11/2019

Semi-supervised Feature-Level Attribute Manipulation for Fashion Image Retrieval

With a growing demand for the search by image, many works have studied t...
research
06/29/2019

Progressive Fashion Attribute Extraction

Extracting fashion attributes from images of people wearing clothing/fas...
research
05/07/2023

Data Efficient Training with Imbalanced Label Sample Distribution for Fashion Detection

Multi-label classification models have a wide range of applications in E...
research
09/16/2021

Semi-Supervised Visual Representation Learning for Fashion Compatibility

We consider the problem of complementary fashion prediction. Existing ap...
research
06/13/2019

c^+GAN: Complementary Fashion Item Recommendation

We present a conditional generative adversarial model to draw realistic ...
research
09/11/2018

Layerwise Perturbation-Based Adversarial Training for Hard Drive Health Degree Prediction

With the development of cloud computing and big data, the reliability of...

Please sign up or login with your details

Forgot password? Click here to reset