Search Results for author:
Found 18 papers, 7 papers with code
Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
To address this, we propose a novel TTA method by leveraging a latent diffusion model (LDM) based image editing model and fine-tuning it with our newly introduced corruption modeling scheme.
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error.
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks.
Ranked #2 on
Visual Prompt Tuning
on VTAB-1k(Natural<7>)
Probabilistic Concept Bottleneck Models
To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM).
Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection
Diffusion-Stego achieved a high capacity of messages (3. 0 bpp of binary messages with 98% accuracy, and 6. 0 bpp with 90% accuracy) as well as high quality (with a FID score of 2. 77 for 1. 0 bpp on the FFHQ 64$\times$64 dataset) that makes it challenging to distinguish from real images in the PNG format.
Sample-efficient Adversarial Imitation Learning
In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions.
New Insights for the Stability-Plasticity Dilemma in Online Continual Learning
The aim of continual learning is to learn new tasks continuously (i. e., plasticity) without forgetting previously learned knowledge from old tasks (i. e., stability).
Generating Instance-level Prompts for Rehearsal-free Continual Learning
However, we observe that the use of a prompt pool creates a domain scalability problem between pre-training and continual learning.
FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks
While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient.
Confidence Score for Source-Free Unsupervised Domain Adaptation
Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge.
Confidence Score Weighting Adaptation for Source-Free Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to achieve high performance within the unlabeled target domain by leveraging the labeled source domain.
Stein Latent Optimization for Generative Adversarial Networks
Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner.
iCaps: An Interpretable Classifier via Disentangled Capsule Networks
We propose an interpretable Capsule Network, iCaps, for image classification.
PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degradation
We propose a DL based steganalysis technique that effectively removes secret images by restoring the distribution of the original images.
HexaGAN: Generative Adversarial Nets for Real World Classification
We evaluate the classification performance (F1-score) of the proposed method with 20% missingness and confirm up to a 5% improvement in comparison with the performance of combinations of state-of-the-art methods.
AnomiGAN: Generative adversarial networks for anonymizing private medical data
We compared our method to state-of-the-art techniques and observed that our method preserves the same level of privacy as differential privacy (DP), but had better prediction results.
PixelSteganalysis: Destroying Hidden Information with a Low Degree of Visual Degradation
The cover image with the secret message is called a stego image.
Security and Privacy Issues in Deep Learning
Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications.
