paper-with-me

홈 › Papers

Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing

2022-03-23 · Hsin-Ping Huang, Deqing Sun, Yaojie Liu, Wen-Sheng Chu, Taihong Xiao, Jinwei Yuan, Hartwig Adam, Ming-Hsuan Yang

While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face antispoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods for cross-domain face anti-spoofing using a few samples.

📄 PDF Abstract BibTeX arXiv:2203.12175

Code (0)

등록된 구현이 없습니다.

Tasks

Face Anti-Spoofing

Similar Papers 제목 키워드 기반

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

2026-06-23 · Mohammed Yusuf Mujawar, Noorbakhsh Amiri Golilarz arxiv

Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary associative information during an episode, but fixed memory behavior m…

Few-Shot Learning

One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers

2022-12-14 · Rui Gong, Qin Wang, Dengxin Dai, Luc van Gool

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-worl…

Autonomous DrivingDomain AdaptationSemantic Segmentation

Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification

2026-01-18 · Anurag Kaushish, Ayan Sar, Sampurna Roy, Sudeshna Chakraborty 외 arxiv

Few-shot learning in remote sensing remains challenging due to three factors: the scarcity of labeled data, substantial domain shifts, and the multi-scale nature of geospatial objects. To address these issues, we introdu…

Remote Sensing Image ClassificationFew-Shot Learning

Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance

2024-12-01 · Zhe Wang, Haozhu Wang, Yanjun Qi

Decision transformers recast reinforcement learning as a conditional sequence generation problem, offering a simple but effective alternative to traditional value or policy-based methods. A recent key development in this…

MuJoCo

Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning

2025-10-21 · Jiaao Yu, Mingjie Han, Jinkun Jiang, Junyu Dong 외 arxiv

The high cost of data annotation has spurred research on training deep learning models in data-limited scenarios. Existing paradigms, however, fail to balance cross-domain transfer and cross-category generalization, givi…

Zero-Shot Learning