paper-with-me

Papers

Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification

2018-08-06 · Tao Hu, Jizheng Xu, Cong Huang, Honggang Qi, Qingming Huang, Yan Lu

For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extracting discriminative local features play a crucial role in accurate category prediction. Existing works either pay attention to limited object parts or train isolated networks for locating and classification. In this paper, we propose Weakly Supervised Bilinear Attention Network (WS-BAN) to solve these issues. It jointly generates a set of attention maps (region-of-interest maps) to indicate the locations of object's parts and extracts sequential part features by Bilinear Attention Pooling (BAP). Besides, we propose attention regularization and attention dropout to weakly supervise the generating process of attention maps. WS-BAN can be trained end-to-end and achieves the state-of-the-art performance on multiple fine-grained classification datasets, including CUB-200-2011, Stanford Car and FGVC-Aircraft, which demonstrated its effectiveness.

📄 PDF Abstract BibTeX arXiv:1808.02152

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationFine-Grained Image ClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

High-Order-Interaction for weakly supervised Fine-Grained Visual Categorization

2021-11-13 · Neurocomputing 2021 11 · Nanyu Li, Junzhen Wang, Zhimin Luo, Zhun Zhong 외

Fine-Grained Visual Categorization (FGVC) is a challenging task due to the large intra-subcategory and small inter-subcategory variances. Recent studies tackle this task through a weakly supervised manner without using t…

Fine-Grained Image ClassificationFine-Grained Image RecognitionFine-Grained Visual CategorizationTriplet+1

DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification

2020-01-04 · ZiChao Dong, JiLong Wu, TingTing Ren, Yue Wang 외

Fine-grained image classification is a challenging problem, since the difficulty of finding discriminative features. To handle this circumstance, basically, there are two ways to go. One is use attention based method to …

Fine-Grained Image Classificationimage-classificationImage Classification

Weakly Supervised Attention Learning for Textual Phrases Grounding

2018-05-01 · Zhiyuan Fang, Shu Kong, Tianshu Yu, Yezhou Yang

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing met…

Fine-Grained Attention for Weakly Supervised Object Localization

2021-04-11 · Junghyo Sohn, Eunjin Jeon, Wonsik Jung, Eunsong Kang 외

Although recent advances in deep learning accelerated an improvement in a weakly supervised object localization (WSOL) task, there are still challenges to identify the entire body of an object, rather than only discrimin…

ObjectObject LocalizationWeakly-Supervised Object Localization

See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

2019-01-26 · Tao Hu, Honggang Qi, Qingming Huang, Yan Lu

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping,…

Data AugmentationFine-Grained Image ClassificationGeneral ClassificationImage Cropping+1