Search Results for author:
Found 16 papers, 14 papers with code
Fisher Information guided Purification against Backdoor Attacks
Intuitively, the backdoor can be purified by re-optimizing the model to smoother minima.
Augmented Neural Fine-Tuning for Efficient Backdoor Purification
In this paper, we propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities in a way that the effect of the backdoor is removed.
Free-Editor: Zero-shot Text-driven 3D Scene Editing
Text-to-Image (T2I) diffusion models have recently gained traction for their versatility and user-friendliness in 2D content generation and editing.
LatentEditor: Text Driven Local Editing of 3D Scenes
Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models, bridging the gap between textual instructions and high-quality 3D scene editing in latent space.
Efficient Backdoor Removal Through Natural Gradient Fine-tuning
Extensive experiments show that the proposed method achieves state-of-the-art performance on a wide range of backdoor defense benchmarks: four different datasets- CIFAR10, GTSRB, Tiny-ImageNet, and ImageNet; 13 recent backdoor attacks, e. g.
SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editing
Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts.
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
In this regard, source-free domain adaptation (SFDA) excels as access to source data is no longer required during adaptation.
Ranked #4 on
Source-Free Domain Adaptation
on VisDA-2017
A Survey of Recommender System Techniques and the Ecommerce Domain
This paper reviews the different techniques and developments of recommender systems in e-commerce, e-tourism, e-resources, e-government, e-learning, and e-library.
CNLL: A Semi-supervised Approach For Continual Noisy Label Learning
After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples.
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection
The method proposed in this work referred to as RODD outperforms SOTA detection performance on an extensive suite of benchmark datasets on OOD detection tasks.
Ranked #1 on
Out-of-Distribution Detection
on cifar100
(using extra training data)
RF Signal Transformation and Classification using Deep Neural Networks
Deep neural networks (DNNs) designed for computer vision and natural language processing tasks cannot be directly applied to the radio frequency (RF) datasets.
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data.
Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuning
Through comparing adversarial robustness achieved without adversarial training, with triplet loss adversarial training, and our contrastive pre-training combined with triplet loss adversarial fine-tuning, we find that our method achieves comparable results with far fewer epochs re-quired during fine-tuning.
SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network
In this paper, we propose a generative adversarial network-based reconstruction framework for single-pixel imaging, referred to as SPI-GAN.
RL-NCS: Reinforcement learning based data-driven approach for nonuniform compressed sensing
The proposed scheme, referred to as RL-NCS, aims to boost the performance of signal recovery through an optimal and adaptive distribution of sensing energy among two groups of coefficients of the signal, referred to as the region of interest (ROI) coefficients and non-ROI coefficients.
Odyssey: Creation, Analysis and Detection of Trojan Models
We propose a detector that is based on the analysis of the intrinsic DNN properties; that are affected due to the Trojaning process.
