Decision Fusion Networks for Image Classification

Tang, Keke; Ma, Yuexin; Miao, Dingruibo; Song, Peng; Gu, Zhaoquan; Tian, Zhihong; Wang, Wenping

doi:10.1109/tnnls.2022.3196129

Cited by 28 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For RPA, we set the ensemble number N to 60, the modify probability p m is set to 0.3 and 0.2 when attacking normally trained models and defense ones respectively. For the proposed SGMA, the ensemble number ens equals to 30, the length of the grid d will be randomly selected in the range of [3,105]. The side length keep-ratio r is 0.5 and 0.6 for the normally training model and defense one respectively, the maximum offset S and the maximum varying of the side length C will vary within d. Our choice of layers to be attacked is the same as that in [31].…”

Section: Hyper-parametersmentioning

confidence: 99%

“…The last decade has witnessed the rapid development of deep neural networks (DNN), convolutional neural networks (CNN), and their applications in various vision-related tasks such as pedestrian trajectory prediction, image restoration, face recognition, and so forth [1][2][3][4][5][6]. Despite the impressive progress, prior studies show that deep learning systems are not always reliable and can be easily misled by carefully designed perturbations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SGMA: a novel adversarial attack approach with improved transferability

Zhu

Hong²,

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Deep learning models are easily deceived by adversarial examples, and transferable attacks are crucial because of the inaccessibility of model information. Existing SOTA attack approaches tend to destroy important features of objects to generate adversarial examples. This paper proposes the split grid mask attack (SGMA), which reduces the intensity of model-specific features by split grid mask transformation, effectively highlighting the important features of the input image. Perturbing these important features can guide the development of adversarial examples in a more transferable direction. Specifically, we introduce the split grid mask transformation into the input image. Due to the vulnerability of model-specific features to image transformations, the intensity of model-specific features decreases after aggregation while the intensities of important features remain. The generated adversarial examples guided by destroying important features have excellent transferability. Extensive experimental results demonstrate the effectiveness of the proposed SGMA. Compared to the SOTA attack approaches, our method improves the black-box attack success rates by an average of 6.4% and 8.2% against the normally trained models and the defense ones respectively.

show abstract

Section: Hyper-parametersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SGMA: a novel adversarial attack approach with improved transferability

Zhu

Hong²,

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Deep Learning for Point Clouds and 2-manifold Representation. Since PointNet (Qi et al 2017a) pioneered the processing of point clouds directly using deep learning techniques (Tang et al 2022b), a large body of researches have been studied (Qi et al 2017b;Wang et al 2019;Li et al 2018;Chen et al 2022;Tang et al 2022a). We aim to evaluate and improve their robustness to adversarial attacks.…”

Section: Related Workmentioning

confidence: 99%

Deep Manifold Attack on Point Clouds via Parameter Plane Stretching

Tang

Peng

et al. 2023

AAAI

View full text Add to dashboard Cite

Adversarial attack on point clouds plays a vital role in evaluating and improving the adversarial robustness of 3D deep learning models. Current attack methods are mainly applied by point perturbation in a non-manifold manner. In this paper, we formulate a novel manifold attack, which deforms the underlying 2-manifold surfaces via parameter plane stretching to generate adversarial point clouds. First, we represent the mapping between the parameter plane and underlying surface using generative-based networks. Second, the stretching is learned in the 2D parameter domain such that the generated 3D point cloud fools a pretrained classifier with minimal geometric distortion. Extensive experiments show that adversarial point clouds generated by manifold attack are smooth, undefendable and transferable, and outperform those samples generated by the state-of-the-art non-manifold ones.

show abstract

“…Deep learning has been successfully applied to a broad range of computer vision tasks, such as image classification [1], [2], [3], object detection [4], [5], [6] and scene segmentation [7], [8], etc. However, when generalizing a trained model to unseen new classes, we need to retrain it from scratch with a large number of labeled samples together with the data from old classes.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty-Guided Semi-Supervised Few-Shot Class-Incremental Learning With Knowledge Distillation

Cui

Deng²,

Xu³

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all encountered classes previously. Currently, semi-supervised learning technique that harnesses freely-available unlabeled data to compensate for limited labeled data can boost the performance in numerous vision tasks, which heuristically can be applied to tackle issues in FSCIL, i.e., the Semi-supervised FSCIL (Semi-FSCIL). So far, very limited work focuses on the Semi-FSCIL task, leaving the adaptability issue of semi-supervised learning to the FSCIL task unresolved. In this paper, we focus on this adaptability issue and present a simple yet efficient Semi-FSCIL framework named Uncertainty-aware Distillation with Class-Equilibrium (UaD-CE), encompassing two modules UaD and CE. Specifically, when incorporating unlabeled data into each incremental session, we introduce the CE module that employs a class-balanced self-training to avoid the gradual dominance of easy-to-classified classes on pseudo-label generation. To distill reliable knowledge from the reference model, we further implement the UaD module that combines uncertainty-guided knowledge refinement with adaptive distillation. Comprehensive experiments on three benchmark datasets demonstrate that our method can boost the adaptability of unlabeled data with the semi-supervised learning technique in FSCIL tasks. The code is available at https://github.com/yawencui/UaD-CE.

show abstract

Decision Fusion Networks for Image Classification

Cited by 28 publications

References 0 publications

SGMA: a novel adversarial attack approach with improved transferability

SGMA: a novel adversarial attack approach with improved transferability

Deep Manifold Attack on Point Clouds via Parameter Plane Stretching

Uncertainty-Guided Semi-Supervised Few-Shot Class-Incremental Learning With Knowledge Distillation

Contact Info

Product

Resources

About