SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.11184 · ECCV · 2022

Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection

Shuang Wu, Wenjie Pei, Dianwen Mei, Guangming Lu, Jiandong Tian, Fanglin Chen

arXiv · PDF · Open in the Atlas

Code that ran

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.

RepositoryRoleRan
wushuang1998/mfdc canonical 2 of 4
FunctionStatusWhere 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")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

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.