Robust and Accurate Object Detection via Adversarial Learning
- URL: http://arxiv.org/abs/2103.13886v1
- Date: Tue, 23 Mar 2021 19:45:26 GMT
- Title: Robust and Accurate Object Detection via Adversarial Learning
- Authors: Xiangning Chen, Cihang Xie, Mingxing Tan, Li Zhang, Cho-Jui Hsieh,
Boqing Gong
- Abstract summary: This work augments the fine-tuning stage for object detectors by exploring adversarial examples.
Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the object detection benchmark.
- Score: 111.36192453882195
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Better Sampling, towards Better End-to-end Small Object Detection [7.7473020808686694]
Small object detection remains unsatisfactory due to limited characteristics and high density and mutual overlap.
We propose methods enhancing sampling within an end-to-end framework.
Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset.
arXiv Detail & Related papers (2024-05-17T04:37:44Z) - Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images [15.12889076965307]
YOLOv7 one-stage detector is subjected to a novel meta-learning training framework.
This transformation allows the detector to adeptly address FSOD tasks while capitalizing on its inherent advantage of lightweight.
To validate the effectiveness of our proposed detector, we conducted performance comparisons with current state-of-the-art detectors.
arXiv Detail & Related papers (2024-04-29T04:56:52Z) - Towards Few-Annotation Learning for Object Detection: Are
Transformer-based Models More Efficient ? [11.416621957617334]
In this paper, we propose a semi-supervised method tailored for the current state-of-the-art object detector Deformable DETR.
We evaluate our method on the semi-supervised object detection benchmarks COCO and Pascal VOC, and it outperforms previous methods, especially when annotations are scarce.
arXiv Detail & Related papers (2023-10-30T18:51:25Z) - FROD: Robust Object Detection for Free [1.8139771201780368]
State-of-the-art object detectors are susceptible to small adversarial perturbations.
We propose modifications to the classification-based backbone to instill robustness in object detection.
arXiv Detail & Related papers (2023-08-03T17:31:22Z) - Learning Object-level Point Augmentor for Semi-supervised 3D Object
Detection [85.170578641966]
We propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection.
In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds.
Experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods.
arXiv Detail & Related papers (2022-12-19T06:56:14Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs.
We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset.
Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
arXiv Detail & Related papers (2022-03-10T23:35:00Z) - Transformer-Encoder Detector Module: Using Context to Improve Robustness
to Adversarial Attacks on Object Detection [12.521662223741673]
This article proposes a new context module that can be applied to an object detector to improve the labeling of object instances.
The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13% compared to the baseline Faster-RCNN detector.
arXiv Detail & Related papers (2020-11-13T15:52:53Z) - DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
Current algorithms suffer from insufficient training samples and category imbalance within datasets.
We propose an efficient and effective data augmentation method called DecAug for HOI detection.
Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
arXiv Detail & Related papers (2020-10-02T13:59:05Z) - Detection as Regression: Certified Object Detection by Median Smoothing [50.89591634725045]
This work is motivated by recent progress on certified classification by randomized smoothing.
We obtain the first model-agnostic, training-free, and certified defense for object detection against $ell$-bounded attacks.
arXiv Detail & Related papers (2020-07-07T18:40:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.