Hierarchical block aggregation network for long-tailed visual recognition
Neurocomputing, ISSN: 0925-2312, Vol: 549, Page: 126463
2023
- 4Citations
- 1Captures
Metric Options: Counts1 Year3 YearSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
It is usually supposed that training database is manually balanced in traditional visual recognition tasks. However, in nature, data tends to follow long-tailed distributions. In recent years, many plug-and-play methods based on data augmentation or representation learning have been proposed to tackle the long-tailed visual recognition task. Although these methods are effective, we find that when different plug-and-play methods are applied to the same long-tail recognition model, they sometimes fail to promote each other. The reason for this phenomenon may lie in the fact that the overall performance of the model is constrained by the insufficient capability of a traditional feature extractor. Motivated by this fact, we first propose Hierarchical Block Aggregation Network (HBAN), a network structure with stronger feature extraction capability. Then, we design a Quantity-Aware Balanced (QAB) loss and a decoupled training paradigm to optimize HBAN. The effectiveness of HBAN is demonstrated by extensive experiments. In particular, HBAN achieves significant improvements over our baseline on three benchmark datasets, and outperforms the state-of-the-art methods on CIFAR 100-LT.
Bibliographic Details
http://www.sciencedirect.com/science/article/pii/S0925231223005866; http://dx.doi.org/10.1016/j.neucom.2023.126463; http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85163046852&origin=inward; https://linkinghub.elsevier.com/retrieve/pii/S0925231223005866; https://dx.doi.org/10.1016/j.neucom.2023.126463
Elsevier BV
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know