Search Results for author:
Found 13 papers, 3 papers with code
Generalized Deepfakes Detection with Reconstructed-Blended Images and Multi-scale Feature Reconstruction Network
The growing diversity of digital face manipulation techniques has led to an urgent need for a universal and robust detection technology to mitigate the risks posed by malicious forgeries.
RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced Categories
To our knowledge, the study of weakly supervised learning from the perspective of data augmentation to deal with the WSI classification problem that suffers from lack of training data and imbalance of categories is relatively unexplored.
DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis
Despite an increased demand for valuable data, the privacy concerns associated with sensitive datasets present a barrier to data sharing.
Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
However, the sensitive information in the datasets discourages data owners from releasing these datasets.
Manifold-aware Training: Increase Adversarial Robustness with Feature Clustering
Inspired by the observation from the distribution properties of the features extracted by the CNNs in the feature space and their link to robustness, this work designs a novel training process called Manifold-Aware Training (MAT), which forces CNNs to learn compact features to increase robustness.
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs
Secondly, we propose a task-agnostic semantics-measured module, which cooperates with the graph representation method, in order to (3) project an edge of a sentence-level graph to the space of semantic relevance with respect to the corresponding concept nodes.
Deterministic Certification to Adversarial Attacks via Bernstein Polynomial Approximation
Theoretical analyses and experimental results indicate that our method is promising for classifier smoothing and robustness certification.
QISTA-Net: DNN Architecture to Solve $\ell_q$-norm Minimization Problem and Image Compressed Sensing
By taking advantage of deep learning in accelerating optimization algorithms, together with the speedup strategy that using the momentum from all previous layers in the network, we propose a learning-based method, called QISTA-Net-s, to solve the sparse signal reconstruction problem.
Difference-Seeking Generative Adversarial Network--Unseen Sample Generation
Unseen data, which are not samples from the distribution of training data and are difficult to collect, have exhibited importance in numerous applications, ({\em e. g.,} novelty detection, semi-supervised learning, and adversarial training).
Greedy Algorithms for Hybrid Compressed Sensing
Considering the fact that the one-bit CS is optimal for the direction estimation of signals under noise with a fixed bit budget and that the traditional CS is able to provide residue information and estimated signals, we focus on the design of greedy algorithms, which consist of the main steps of support detection and recovered signal update, for the hybrid CS in this paper.
Difference-Seeking Generative Adversarial Network
DSGAN considers the scenario that the training samples of target distribution, $p_{t}$, are difficult to collect.
Fast Binary Embedding via Circulant Downsampled Matrix -- A Data-Independent Approach
Binary embedding of high-dimensional data aims to produce low-dimensional binary codes while preserving discriminative power.
Fast Template Matching by Subsampled Circulant Matrix
Template matching is widely used for many applications in image and signal processing and usually is time-critical.
