Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition

• URL: http://arxiv.org/abs/2004.02684v2
• Date: Thu, 9 Jul 2020 09:52:23 GMT
• Title: Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
• Authors: Hao Li, Xiaopeng Zhang, Hongkai Xiong, Qi Tian
• Abstract summary: We propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples. The principle lies in that attribute features are shared among fine-grained sub-categories, and can be seamlessly transferred among images.
• Score: 102.45926816660665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up. In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples. The principle lies in that attribute features are shared among fine-grained sub-categories, and can be seamlessly transferred among images. Toward this goal, we propose an automatic attribute mining approach to discover attributes that belong to the same super-category, and Attribute Mix is operated by mixing semantically meaningful attribute features from two images. Attribute Mix is a simple but effective data augmentation strategy that can significantly improve the recognition performance without increasing the inference budgets. Furthermore, since attributes can be shared among images from the same super-category, we further enrich the training samples with attribute level labels using images from the generic domain. Experiments on widely used fine-grained benchmarks demonstrate the effectiveness of our proposed method.

Related papers

• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval [65.43522019468976]
  We propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes. We develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors. Our models are equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities.
  arXiv  Detail & Related papers  (2023-11-21T08:20:38Z)
• Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval [24.8065557159198]
  We propose an Attributes Grouping and Mining Hashing (AGMH) for fine-grained image retrieval. AGMH groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation. AGMH consistently yields the best performance against state-of-the-art methods on fine-grained benchmark datasets.
  arXiv  Detail & Related papers  (2023-11-10T14:01:56Z)
• Attribute Prototype Network for Any-Shot Learning [113.50220968583353]
  We argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. We propose a novel representation learning framework that jointly learns global and local features using only class-level attributes.
  arXiv  Detail & Related papers  (2022-04-04T02:25:40Z)
• Multi-Objective Few-shot Learning for Fair Classification [23.05869193599414]
  We propose a framework for mitigating the disparities of the predicted classes with respect to secondary attributes within the data. Our proposed method involves learning a multi-objective function that in addition to learning the primary objective of predicting the primary class labels from the data, also employs a clustering-based to minimize the disparities of the class label distribution with respect to the cluster memberships.
  arXiv  Detail & Related papers  (2021-10-05T11:28:58Z)
• Effectively Leveraging Attributes for Visual Similarity [52.2646549020835]
  We propose the Pairwise Attribute-informed similarity Network (PAN), which breaks similarity learning into capturing similarity conditions and relevance scores from a joint representation of two images. PAN obtains a 4-9% improvement on compatibility prediction between clothing items on Polyvore Outfits, a 5% gain on few shot classification of images using Caltech-UCSD Birds (CUB), and over 1% boost to Recall@1 on In-Shop Clothes Retrieval.
  arXiv  Detail & Related papers  (2021-05-04T18:28:35Z)
• Matched sample selection with GANs for mitigating attribute confounding [30.488267816304177]
  We propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes. Our matching approach first projects real images onto a generative network's latent space in a manner that preserves semantic attributes. It then finds adversarial matches in this latent space across a chosen protected attribute, yielding a dataset where semantic and perceptual attributes are balanced across the protected attribute.
  arXiv  Detail & Related papers  (2021-03-24T19:18:44Z)
• Learning to Infer Unseen Attribute-Object Compositions [55.58107964602103]
  A graph-based model is proposed that can flexibly recognize both single- and multi-attribute-object compositions. We build a large-scale Multi-Attribute dataset with 116,099 images and 8,030 composition categories.
  arXiv  Detail & Related papers  (2020-10-27T14:57:35Z)
• SMILE: Semantically-guided Multi-attribute Image and Layout Editing [154.69452301122175]
  Attribute image manipulation has been a very active topic since the introduction of Generative Adversarial Networks (GANs) We present a multimodal representation that handles all attributes, be it guided by random noise or images, while only using the underlying domain information of the target domain. Our method is capable of adding, removing or changing either fine-grained or coarse attributes by using an image as a reference or by exploring the style distribution space.
  arXiv  Detail & Related papers  (2020-10-05T20:15:21Z)
• MulGAN: Facial Attribute Editing by Exemplar [2.272764591035106]
  Methods encode attribute-related information in images into the predefined region of the latent feature space by employing a pair of images with opposite attributes as input to train model. They suffer from three limitations: (1) the model must be trained using a pair of images with opposite attributes as input; (2) weak capability of editing multiple attributes by exemplars; and (3) poor quality of generating image.
  arXiv  Detail & Related papers  (2019-12-28T04:02:15Z)

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.