Boqing Gong, Cho-Jui Hsieh, Xiangning Chen, Mingxing Tan, Cihang Xie, Li Zhang
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.
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a pre-trained classifier, we first study how the classifiers' gains from various data augmentations transfer to object detection. The results are discouraging; the gains diminish after fine-tuning in terms of either accuracy or robustness. This work instead augments the fine-tuning stage for object detectors by exploring adversarial examples, which can be viewed as a model-dependent data augmentation. Our method dynamically selects the stronger adversarial images sourced from a detector's classification and localization branches and evolves with the detector to ensure the augmentation policy stays current and relevant. This model-dependent augmentation generalizes to different object detectors better than AutoAugment, a model-agnostic augmentation policy searched based on one particular detector. Our approach boosts the performance of state-ofthe-art EfficientDets by +1.1 mAP on the COCO object detection benchmark. It also improves the detectors' robustness against natural distortions by +3.8 mAP and against domain shift by +1.3 mAP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.13886")
get_code_for_paper("2103.13886")
have("2103.13886")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.13886.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.13886)
Connect an agent — have() is free.