Anh Nguyen, Shan Luo, Jiankang Deng, Konstantinos Panagiotis
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant performance gap between rare and frequent categories. In this paper, we identify that Sigmoid or Softmax functions used in deep detectors are a major reason for low performance and are suboptimal for long-tailed detection and segmentation. To address this, we develop a Gumbel Optimized Loss (GOL), for long-tailed detection and segmentation. It aligns with the Gumbel distribution of rare classes in imbalanced datasets, considering the fact that most classes in long-tailed detection have low expected probability. The proposed GOL significantly outperforms the best state-of-the-art method by 1.1% on AP , and boosts the overall segmentation by 9.0% and detection by 8.0%, particularly improving detection of rare classes by 20.3%, compared to Mask-RCNN, on LVIS dataset. Code available at: https://github.com/kostas1515/ GOL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.10936")
get_code_for_paper("2207.10936")
have("2207.10936")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2207.10936.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2207.10936)
Connect an agent — have() is free.