Shuang Wu, Wenjie Pei, Dianwen Mei, Guangming Lu, Jiandong Tian, Fanglin Chen
We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| wushuang1998/mfdc | canonical | 2 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| filter_images_with_few_keypoints | Ran | wushuang1998/mfdc/defrcn/dataloader/build.py code served (permissive licence) · get_code("9517da58a95bac43") |
| filter_images_with_only_crowd_annotations | Ran | wushuang1998/mfdc/defrcn/dataloader/build.py code served (permissive licence) · get_code("4c8a4908e88089ef") |
| concat_all_gather | Not yet run | wushuang1998/mfdc/defrcn/evaluation/calibration_layer.py code served (permissive licence) · get_code("73cecca9f3575f09") |
| get_save_path_seeds | Not yet run | wushuang1998/mfdc/datasets/prepare_coco_few_shot.py code served (permissive licence) · get_code("55cc9fdee3a4cd0a") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the classagnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy. However, it is not necessarily true since the object detector can hardly distinguish between class-agnostic knowledge and class-specific knowledge automatically without explicit modeling. In this work we propose to learn three types of class-agnostic commonalities between base and novel classes explicitly: recognition-related semantic commonalities, localization-related semantic commonalities and distribution commonalities. We design a unified distillation framework based on a memory bank, which is able to perform distillation of all three types of commonalities jointly and efficiently. Extensive experiments demonstrate that our method can be readily integrated into most of existing fine-tuning based methods and consistently improve the performance by a large margin.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.11184")
get_code_for_paper("2207.11184")
have("2207.11184")
Connect an agent — have() is free.