Robust and Accurate Object Detection via Adversarial Learning

03/23/2021
by   Xiangning Chen, et al.
10

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-of-the-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.

READ FULL TEXT
06/26/2019

Learning Data Augmentation Strategies for Object Detection

Data augmentation is a critical component of training deep learning mode...
12/06/2021

Seeing BDD100K in dark: Single-Stage Night-time Object Detection via Continual Fourier Contrastive Learning

Despite tremendous improvements in state-of-the-art object detectors, ad...
07/04/2022

A Robust Ensemble Model for Patasitic Egg Detection and Classification

Intestinal parasitic infections, as a leading causes of morbidity worldw...
04/14/2022

OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes

We propose a one-step person detector for topview omnidirectional indoor...
01/04/2021

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

Deep learning based object detectors are commonly deployed on mobile dev...
08/01/2021

An Effective and Robust Detector for Logo Detection

In recent years, intellectual property (IP), which represents literary, ...
11/04/2021

Bootstrap Your Object Detector via Mixed Training

We introduce MixTraining, a new training paradigm for object detection t...

Code Repositories

mmdet-tf

RE IMPLEMENT MMDET TORCH BUT WITH TENSORFLOW-TF2


view repo