A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Fabio Galbusera, Gloria Casaroli, Tito Bassani
A narrative review of AI and ML techniques applied to spine research, covering localization, segmentation, diagnosis, outcome prediction, decision support, and ethical issues.
Unknown
DeepSeekMoE introduces a novel MoE architecture with fine-grained expert segmentation and shared experts to achieve ultimate expert specialization in language models.
Unknown
This paper introduces GSVA, a generalized segmentation framework using multimodal large language models to enable flexible, instruction-driven segmentation across diverse visual tasks.
Jo Schlemper, Ozan Oktay, Michiel Schaap, et al.
Introduces attention gates for CNNs that automatically learn to focus on salient regions in medical images, improving classification and segmentation performance without external localization modules.
Eduardo Romera, Jose M. Álvarez, Luis M. Bergasa, et al.
ERFNet introduces a novel efficient residual factorized convolutional layer for real-time semantic segmentation, achieving high accuracy at over 83 FPS on Titan X and 7 FPS on Jetson TX1.
Chunming Li, Chenyang Xu, Changfeng Gui, et al.
Proposes a variational level set formulation with a distance regularization term that eliminates the need for reinitialization, enabling stable and efficient image segmentation.
Patrick Bilic, Patrick Ferdinand Christ, Hongwei Li, et al.
The LiTS benchmark evaluates liver and tumor segmentation algorithms on a diverse CT dataset, finding no single algorithm excels at both tasks and highlighting the need for improved tumor detection.
Felix Gremse, Marius Stärk, Josef Ehling, et al.
A GPU-accelerated software tool for interactive segmentation and rendering of multimodal biomedical volume data.
Konstantinos Kamnitsas, Christian Ledig, Virginia Newcombe, et al.
A dual-pathway 3D CNN with dense training and fully connected CRF achieves state-of-the-art brain lesion segmentation across multiple pathologies.
Evan Shelhamer, Jonathan Long, Trevor Darrell
Fully convolutional networks trained end-to-end for semantic segmentation achieve state-of-the-art results by adapting classification nets and using a skip architecture for detailed predictions.
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, et al.
DeepLab advances semantic segmentation via atrous convolution, ASPP, and fully connected CRFs, achieving state-of-the-art on multiple benchmarks.
Yuqi Han, Huaping Liu, Yufeng Wang, et al.
A comprehensive review of recent UAV vision techniques for object detection, tracking, and semantic segmentation, highlighting challenges and future directions.