EFCN, Aggregate Contexts Using Convolutional Context Network (CCN) — Toward Achieving Robust Low-Level and High-Level Scene Parsing, EFCN, by Nanyang Technological University, and Alibaba AI Labs, 2019 TIP, Over 25 Citations (Sik-Ho Tsang @ Medium) Semantic Segmentation, Fully Convolutional Network, FCN It is found that the parsing performance of “skip” network can be noticeably improved by modifying the parameterization…

MobileOne, Low Latency Design for Image Classification — An Improved One millisecond Mobile Backbone, MobileOne, by Apple, 2022 arXiv v1, Over 5 Citations (Sik-Ho Tsang @ Medium) Image Classification Extensive analysis of different metrics is performed by deploying several mobile-friendly networks on a mobile device. An efficient backbone MobileOne, with variants achieving an inference time under 1 ms…

U-Net as Segmentation Network + RF as Post Processing — Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing, FCN+RF, by Fraunhofer Institute for Medical Image Computing MEVIS, Radboud University Medical Center, Jacobs University, and University of Bremen, 2018 Nature Sci. Rep., Over 170 Citations (Sik-Ho Tsang @ Medium) Medical Image Analysis, Medical Imaging, Image Segmentation, U-Net…

Res2Net, Enhances ResNet Basic Block — Res2Net: A New Multi-scale Backbone Architecture, Res2Net, by Nankai University, UC Merced, and Oxford University, 2021 TPAMI, Over 1300 Citations (Sik-Ho Tsang ＠ Medium) Image Classification, ResNet Res2Net is proposed, which constructs hierarchical residual-like connections within one single residual block. …

U-Net for CMR Image Segmentation — Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR Images, Chen FCVM’20, by Imperial College London, University College London, St Bartholomew’s Hospital, Queen Mary University of London, and University of Oxford, 2020 Front. Cardiovasc. Med., Over 80 Citations (Sik-Ho Tsang @ Medium) Medical Imaging, Medical Image Analysis, Image Segmentation

DeBERTa, First Single Model to Surpass Human Performance on SuperGLUE — DeBERTa: Decoding-enhanced BERT with Disentangled Attention, DeBERTa, by Microsoft Dynamics 365 AI, Microsoft Research 2021 ICLR, Over 700 Citations (Sik-Ho Tsang @ Medium) Natural Language Processing, NLP, Language Model, LM, Transformer, BERT DeBERTa (Decoding-enhanced BERT with disentangled attention) that improves the BERT and RoBERTa models using two novel techniques.

Recurrent U-Net (R-UNet) for Budget Concerned Application — Recurrent U-Net for Resource-Constrained Segmentation, Recurrent U-Net (R-UNet), by CVLab, EPFL, 2019 ICCV, Over 80 Citations (Sik-Ho Tsang @ Medium) Semantic Segmentation, U-Net Very deep networks are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. A novel…

DIU-Net, Using DenseNet and Inception-v3 Concepts in U-Net — DENSE-INception U-Net for Medical Image Segmentation, DIU-Net, by Northeastern University, and Ulster University, 2020 J. CMPB, Over 120 Citations (Sik-Ho Tsang @ Medium) Medical Imaging, Medical Image Analysis, Image Segmentation DENSE-INception U-Net (DIU-Net) is proposed, that integrates the Inception-Res module and densely connecting convolutional module into the U-Net architecture.

YOLACT++, Extends YOLACT (You Only Look At CoefficienTs) — YOLACT++ Better Real-Time Instance Segmentation, YOLACT++, by Georgia Institute of Technology, and University of California, Davis, 2022 TPAMI, Over 270 Citations (Sik-Ho Tsang @ Medium) Instance Segmentation, Semantic Segmentation, YOLACT By extending YOLACT, YOLACT++ is proposed, by incorporating deformable convolutions into the backbone network, optimizing the prediction head with better…