CVPR 2021 is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.
Now the 2021 paper has not been fully released, and will be updated directly when it is released later. Now let’s review the 2020 and 2019 papers.
1.GhostNet: More Features from Cheap Operations (over the architecture of Mobilenet v3) Paper link: https://arxiv.org/pdf/1911.11907 arxiv.org model (amazing performance on ARM CPU): https://github. com/iamhankai/ghostnetgithub.com
We beat other SOTA lightweight CNNs such as MobileNetV3 and FBNet.
AdderNet: Do We Really Need Multiplications in Deep Learning? (Additive Neural Network) Achieved very good performance on large-scale neural networks and datasets. Link to the paper: https://arxiv.org/pdf/1912.13200arxiv.org
Frequency Domain Compact 3D Convolutional Neural Networks (3dCNN compression) Paper link: https://arxiv.org/pdf/1909.04977arxiv.org Open source code: https://github.com/huawei-noah/CARSgithub.com
A Semi-Supervised Assessor of Neural Architectures (NAS)
CARS: Contunuous Evolution for Efficient Neural Architecture Search (Continuously evolved NAS) is efficient, has multiple advantages of differentiability and evolution, and can output Pareto pre-research
On Positive-Unlabeled Classification in GAN (PU+GAN)
Learning multiview 3D point cloud registration (3D point cloud) Link to the paper: arxiv.org/abs/2001.05119
Multi-Modal Domain Adaptation for Fine-Grained Action Recognition (fine-grained action recognition) Link to the paper: arxiv.org/abs/2001.09691
Action Modifiers: Learning from Adverbs in Instructional Video Link to the paper: arxiv.org/abs/1912.06617
Rethinking Performance Estimation in Neural Architecture Search (NAS) Since the real time-consuming part of block wise neural architecture search is performance estimation, this article finds the optimal parameters for block wise NAS, which is faster and more relevant.
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network Paper address: https://arxiv.org/abs/2002.10200 Code: https://github.com/Yuliang-Liu/bezier_curve_text_spotting,https://github. com/aim-uofa/adet