Tag: benchmark datasets

A sine-guided Transformer–CNN network significantly outperformed 21 comparison methods on three benchmark datasets for salient-object detection in optical remote-sensing imagery.

A benchmark study found that concurrency-aware AI achieved up to 98.9% intrusion-detection accuracy, 2.1-times throughput and 57.5% lower average latency ...

A weighted training method that distinguishes likely shortcut examples improved AI robustness across four image and language benchmarks without adding ...

A case-level audit of a public thyroid imaging archive finds contradictory labels, leak-prone data splits, and strong evidence that deep ...

Oxford researchers argue that the common practice of reducing expert annotations to single binary masks introduces a hidden source of ...

Researchers at East China Jiaotong University have developed DE-SVDD, a dual-encoder framework that separates reconstruction learning from one-class boundary modeling ...

Researchers at the University of the Punjab have introduced HumCareADL, a demographically diverse multimodal wearable dataset, and HyMCL-Net, a hybrid ...

A new systematic review finds that hybrid deep learning and metaheuristic optimization frameworks achieve 98 to 100 percent accuracy in ...

Researchers in Guangzhou have developed a graph-based multi-view clustering method built on maximin optimization that comes with a theorem guaranteeing ...

Researchers have developed ALTAI, a neural network that aligns character, word, and semantic representations through cross-granularity contrastive learning to achieve ...