Search Results for author:
Found 9 papers, 8 papers with code
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
In particular, the memory bank is dynamically updated by selecting low-entropy and label-consistent samples in a class-balanced manner.
Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection
The deepfake threats to society and cybersecurity have provoked significant public apprehension, driving intensified efforts within the realm of deepfake video detection.
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Extensive results on 17 datasets validate that our method surpasses or achieves comparable results with state-of-the-art methods on few-shot classification, imbalanced learning, and out-of-distribution generalization.
Self-training solutions for the ICCV 2023 GeoNet Challenge
Our solution adopts a two-stage source-free domain adaptation framework with a Swin Transformer backbone to achieve knowledge transfer from the USA (source) domain to Asia (target) domain.
Unleashing the power of Neural Collapse for Transferability Estimation
Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all.
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
The emergence of vision-language models, such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks.
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
To implement this benchmark, we have developed a unified framework in PyTorch, which allows for consistent evaluation and comparison of the TTA methods across the different datasets and network architectures.
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
To address this issue, we propose a model preprocessing framework, named AdaptGuard, to improve the security of model adaptation algorithms.
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source domain by the nearest neighbors of the prototypes to bridge the unseen source domain and the target domain.
