assent
发表于 2025-3-23 09:45:11
http://reply.papertrans.cn/67/6637/663641/663641_11.png
狂怒
发表于 2025-3-23 15:24:38
Adversarial Deep Learning with Stackelberg Gamest such vulnerabilities in deep networks. These methods focus on attacking and retraining deep networks with adversarial examples to do either feature manipulation or label manipulation or both. In this paper, we propose a new adversarial learning algorithm for finding adversarial manipulations to de
coltish
发表于 2025-3-23 20:40:23
Enhance Feature Representation of Dual Networks for Attribute Predictionition accuracy. In this paper, we propose a novel dual branch adversarial neural network named D-BANN. Inspired by adversarial learning, we drive parallel networks to extract complementary features and adopt a novel loss function to extend the application domain of the model. Moreover, we divide the
强制令
发表于 2025-3-24 00:25:39
Data Augment in Imbalanced Learning Based on Generative Adversarial Networksansformation for data augment to imbalanced datasets. Due to those methods learn from local information, they might generate noisy samples in the dataset with high dimension and special complexity. To solve the problem, we propose an improved Generative Adversarial Networks with modification functio
巡回
发表于 2025-3-24 03:14:24
A Deep Learning Scheme for Extracting Pedestrian-Parcel Tuples from Videostween pedestrians and parcels is an important task in an intelligent security inspection system. However, it is very challenging due to the high pedestrian volume in these places. In this paper, we propose a deep learning scheme for extracting pedestrian-parcel tuples from camera videos, which inclu
光明正大
发表于 2025-3-24 10:27:05
http://reply.papertrans.cn/67/6637/663641/663641_16.png
gentle
发表于 2025-3-24 12:20:01
http://reply.papertrans.cn/67/6637/663641/663641_17.png
Preserve
发表于 2025-3-24 16:28:44
A Gradient-Based Algorithm to Deceive Deep Neural Networksognition of these networks is unstable to slight perturbations of images. To verify this weakness, we propose ., a gradient-based algorithm for deceiving deep neural networks in this paper. There exists a lot of gradient-based attack methods, such as the L-BFGS, FGSM, and Deepfool. Specifically, bas
RAGE
发表于 2025-3-24 22:57:54
Writing Style Adversarial Network for Handwritten Chinese Character Recognitionpeople pay attention to the influence of writing style on it. In this paper, we aim to improve the performance of HCCR further by weakening the influence of different writing styles. We propose a writing style adversarial network (WSAN) which includes three parts: feature extractor, character classi
食草
发表于 2025-3-25 00:15:18
http://reply.papertrans.cn/67/6637/663641/663641_20.png