Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by the success of convolutional neural networks in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations of the problem to solve that affect the output in a predictable way. This promises an increased data efficiency and more interpretable network outputs. In this survey, we try to give a concise overview about different approaches that incorporate geometrical prior knowledge into neural networks. Additionally, we connect those methods to 3D object detection for autonomous driving, where we expect promising results when applying those methods.
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors
Dalian University of Technology(大连理工大学);The Hong Kong Polytechnic University(香港理工大学);The Pennsylvania State University(宾夕法尼亚州立大学);Shenzhen MSU-BIT University(深圳北理莫斯科大学);Zhejiang Lab(之江实验室)
PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
Chongqing University of Technology(重庆理工大学);Chongqing University(重庆大学);The Chinese University of Hong Kong(香港中文大学);SmartMore(智谱AI);University of Macau(澳门大学)
Boosting Ultrasound Image Classification via Attribute-Guided Dual-Branch Framework
School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University(武汉大学计算机学院、国家多媒体软件工程技术研究中心、人工智能研究院、湖北省多媒体与网络通信工程重点实验室)
Boosting Image Restoration via Priors from Pre-trained Models
Zhejiang Lab(之江实验室);CUHK(香港中文大学);RealityEdge(睿迪智芯);University of Macau(澳门大学);Institute of Collaborative Innovation(协同创新研究院);Texas A&M University(德克萨斯农工大学);National University of Singapore(新加坡国立大学);Zhejiang University(浙江大学)
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
School of Electronic and Information Engineering, South China University of Technology(华南理工大学电子与信息工程学院);Peng Cheng Laboratory(鹏城实验室);Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Boosting HDR Image Reconstruction via Semantic Knowledge Transfer
School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院);Shenzhen Research Institute of Northwestern Polytechnical University(西北工业大学深圳研究院);School of Astronautics, Northwestern Polytechnical University(西北工业大学航天学院);Shaanxi University of Science & Technology(陕西科技大学);Xi’an University of Architecture and Technology(西安建筑科技大学);Chinese University of Hong Kong(香港中文大学)
GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Shenzhen ShenNong Information Technology Co., Ltd.(深圳神农信息技术有限公司);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt
Northwestern Polytechnical University(西北工业大学);Zhejiang Lab(之江实验室);Inception Institute of Artificial Intelligence(起源人工智能研究院);University of Chinese Academy of Sciences(中国科学院大学);NetEase(网易);Huazhong University of Science and Technology(华中科技大学)
Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts
Shanghai Artificial Intelligence Lab(上海人工智能实验室);Johns Hopkins University(约翰斯·霍普金斯大学);University of California Santa Cruz(加利福尼亚大学圣克鲁兹分校);West China Biomedical Big Data Center, Sichuan University West China Hospital(四川大学华西医院华西生物医学大数据中心)
Boosting Neural Representations for Videos with a Conditional Decoder
The Hong Kong University of Science and Technology(香港科技大学);SenseTime Research(商汤科技研究院);The Chinese University of Hong Kong(香港中文大学);Beijing Institute of Technology(北京理工大学);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院)