Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization

By Zhe Xu, Shaoli Huang, Ya Zhang, Dacheng Tao. 2015

85 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Yi Yang
6. Andrea Vedaldi
7. Alan L. Yuille
8. G. Wang

Citations in the corpus

• AutoML: A Survey of the State-of-the-Art (2019, background): “A common solution is to fine-tune these web data [68], [69].”
• Recent advances in convolutional neural networks (2015, background): “[116] offer additional means of collecting images from the Internet to improve learning in fine-grained recognition tasks.”
• The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Most fine-grained research papers present a novel model for classification [4, 6, 7, 12, 15, 17, 25, 31, 40, 45, 46, 57, 58, 59, 61, 62].”
• Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “[150] investigated if fine-grained web images could provide weakly-labeled information to augment deep features and thus contribute to robust object classifiers by building a multi-instance (MI) learner, i.”
• Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-Grained Classification (2018, methodology): “In [48], web data together with additional bounding box annotations are required.”
• Part-Stacked CNN for Fine-Grained Visual Categorization (2015, background): “Inspiringly, huge progress has been made over the last few years [40, 4, 39, 18, 45], making fine-grained recognition techniques a large step closer to practical use in various applications, such as wildlife observation and surveillance systems.”
• Visual Concept Recognition and Localization via Iterative Introspection (2016, unknown): “9%) and/or strong supervision [32] (84.”
• Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition (2016, methodology): “[27] use additional web data for training and achieve slight higher performance (0.”
• Recognition From Web Data: A Progressive Filtering Approach (2018, unknown): “In the literature, in an attempt to address this problem, a fine-tuning process can be conducted on the web data [6], [7].”
• Do We Really Need to Collect Millions of Faces for Effective Face Recognition? (2016, background): “They, as well as [41], do not synthesize new data as we propose to do here, but rather offer additional means of collecting images from the Internet to improve learning in fine grained recognition tasks.”