Jian Peng, Lei Zhang, Yu-Xiong Wang, Jianfeng Wang, Lijuan Wang, Yuanyi Zhong
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.
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pretraining, but is specifically tailored to benefit object detection tasks. In contrast to the widely used image classification-based pre-training (e.g., on ImageNet), which does not include any location-related training tasks, we transform a classification dataset into a detection dataset through a weakly supervised object localization method based on Class Activation Maps to directly pre-train a detector, making the pre-trained model location-aware and capable of predicting bounding boxes. We show that DAP can outperform the traditional classification pre-training in terms of both sample efficiency and convergence speed in downstream detection tasks including VOC and COCO. In particular, DAP boosts the detection accuracy by a large margin when the number of examples in the downstream task is small.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.16651")
get_code_for_paper("2103.16651")
have("2103.16651")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.16651.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.16651)
Connect an agent — have() is free.