Search Results for author:
Found 20 papers, 10 papers with code
Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness
This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection.
TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis
Motivated by these insights, we introduce a Text-oriented Cross-Attention Network (TCAN), emphasizing the predominant role of the text modality in MSA.
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models.
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
Instead of relying solely on category-specific annotations, ProLab uses descriptive properties grounded in common sense knowledge for supervising segmentation models.
Corrupting Convolution-based Unlearnable Datasets with Pixel-based Image Transformations
Through validation experiments that commendably support our hypothesis, we further design a random matrix to boost both $\Theta_{imi}$ and $\Theta_{imc}$, achieving a notable degree of defense effect.
Generalized Rainbow Differential Privacy
In this framework, datasets are nodes in a graph, and two neighboring datasets are connected by an edge.
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
In this work, we propose AdvCLIP, the first attack framework for generating downstream-agnostic adversarial examples based on cross-modal pre-trained encoders.
Downstream-agnostic Adversarial Examples
AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration
We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images, which validates our method could achieve the state-of-the-art performance.
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label.
Neural Network Compression via Effective Filter Analysis and Hierarchical Pruning
Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm is developed to maximally condense the neuronal network structure without sacrificing network performance.
Rainbow Differential Privacy
We extend a previous framework for designing differentially private (DP) mechanisms via randomized graph colorings that was restricted to binary functions, corresponding to colorings in a graph, to multi-valued functions.
Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?
Binocular Mutual Learning for Improving Few-shot Classification
From the perspective of class space on base set, existing methods either focus on utilizing all classes under a global view by normal pretraining, or pay more attention to adopt an episodic manner to train meta-tasks within few classes in a local view.
So-ViT: Mind Visual Tokens for Vision Transformer
Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification.
Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation
These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images.
Diffusion model and analysis of diffusion process at lagrangian method
Based on Fick's 2nd law the development of moving particle semi-implicit method for predicting diffusion process is proposed in this study
Fluid Dynamics
Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection
In this paper, based on the fact that salient areas in videos are relatively small and concentrated, we propose a \textbf{key salient object re-augmentation method (KSORA) using top-down semantic knowledge and bottom-up feature guidance} to improve detection accuracy in video scenes.
SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection
To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance.
