Tag: domain adaptation

Researchers in Tokyo have developed a transfer learning framework that encodes the topology of a source domain's feature space into ...

A new framework combining policy gradient adversarial networks with MMD-guided sample transfer lifts machine translation BLEU scores to 39.5 and ...

Researchers combined single-particle fluorescence, optical morphology, and machine learning with domain adaptation to better distinguish biological aerosols from dust, sea ...

Researchers in Vietnam have developed WGPose-LL, a deep learning method that uses paired well-lit images to guide human pose estimation ...

A new Perspective proposes a system-level framework of transferable predictive maintenance that keeps battery health predictions reliable as storage assets ...

A new few-shot object detection framework called FUSED-Net detects traffic signs with up to 2.4 times better accuracy than state-of-the-art ...

Researchers have developed DELTA, an unsupervised domain adaptation model that combines a grouped divergence attention module with self-paced deep clustering ...

Researchers in India show that training only a 2.4-million-parameter projection module on top of frozen CLIP encoders lifts fashion image-to-text ...

A sweeping new survey in Vicinagearth maps the algorithms, applications, and open challenges of transfer metric learning, the technique that ...

A new survey of 161 studies maps how out-of-distribution data undermines AI-based mechanical fault diagnosis and argues that generalization, calibrated ...