Deep learning-based methods in computational microscopy have been shown to be powerful but in general face some challenges due to limited generalization to new types of samples and requirements for large and diverse training data. Here, we demonstrate a few-shot transfer learning method that helps a holographic image reconstruction deep neural network rapidly generalize to new types of samples using small datasets. We pre-trained a convolutional recurrent neural network on a large dataset with diverse types of samples, which serves as the backbone model. By fixing the recurrent blocks and transferring the rest of the convolutional blocks of the pre-trained model, we reduced the number of trainable parameters by ~90% compared with standard transfer learning, while achieving equivalent generalization. We validated the effectiveness of this approach by successfully generalizing to new types of samples using small holographic datasets for training, and achieved (i) ~2.5-fold convergence speed acceleration, (ii) ~20% computation time reduction per epoch, and (iii) improved reconstruction performance over baseline network models trained from scratch. This few-shot transfer learning approach can potentially be applied in other microscopic imaging methods, helping to generalize to new types of samples without the need for extensive training time and data.
National Technical University of Athens（雅典国立技术大学）；University of Macedonia（马其顿大学）
Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures. However, current learning schemes are static, implying no dynamic adaptation to users' feedback. To address this drawback, we present a few-shot learning paradigm for the automated segmentation of road cracks, which is based on a U-Net architecture with recurrent residual and attention modules (R2AU-Net). The retraining strategy dynamically fine-tunes the weights of the U-Net as a few new rectified samples are being fed into the classifier. Extensive experiments show that…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；California Nano Systems Institute (CNSI)（加州纳米系统研究所）；David Geffen School of Medicine, University of California, Los Angeles（加利福尼亚大学洛杉矶分校大卫·格芬医学院）
Digital holography is one of the most widely used label-free microscopy techniques in biomedical imaging. Recovery of the missing phase information of a hologram is an important step in holographic image reconstruction. Here we demonstrate a convolutional recurrent neural network (RNN) based phase recovery approach that uses multiple holograms, captured at different sample-to-sensor distances to rapidly reconstruct the phase and amplitude information of a sample, while also performing autofocusing through the same network. We demonstrated the success of this deep learning-enabled holography me…
Western Washington University（西华盛顿大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little work has been done on few-shot video classification. In this work, we address the task of few-shot video action recognition with a set of two-stream models. We evaluate the performance of a set of convolutional and recurrent neural network video encoder architectures used in conjunction with three popular metric-based few-shot algorithms. We train and evaluate…
Rochester Institute of Technology（罗切斯特理工学院）；Pennsylvania State University（宾夕法尼亚州立大学）
Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over many time steps, making the process of conducting credit assignment considerably more challenging. Furthermore, the nature of back-propagation itself does not permit the use of non-differentiable activation functions and is inherently sequential, making parallelization of the underlying training process difficult. Here, we propose the Parallel Temporal Neural …
Standard deep learning systems require thousands or millions of examples to learn a concept, and cannot integrate new concepts easily. By contrast, humans have an incredible ability to do one-shot or few-shot learning. For instance, from just hearing a word used in a sentence, humans can infer a great deal about it, by leveraging what the syntax and semantics of the surrounding words tells us. Here, we draw inspiration from this to highlight a simple technique by which deep recurrent networks can similarly exploit their prior knowledge to learn a useful representation for a new word from littl…
We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptotic error rates than discriminatively trained RNN models. However we also find that generative models approach their asymptotic error rate more rapidly than their discriminative counterparts---the same pattern that Ng & Jordan (2001) proved holds for linear classification models th…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Uber ATG（优步先进技术集团）
Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without re-training on the full training set. This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the over…
NTT Communication Science Laboratories（NTT通信科学实验室）；NTT Software Innovation Center（NTT软件创新中心）
Time-series forecasting is important for many applications. Forecasting models are usually trained using time-series data in a specific target task. However, sufficient data in the target task might be unavailable, which leads to performance degradation. In this paper, we propose a few-shot learning method that forecasts a future value of a time-series in a target task given a few time-series in the target task. Our model is trained using time-series data in multiple training tasks that are different from target tasks. Our model uses a few time-series to build a forecasting function based on a…
Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring
Lucerne University of Applied Sciences and Arts（卢塞恩应用科学与艺术大学）；Federal Office of Meteorology and Climatology MeteoSwiss（瑞士联邦气象与气候学办公室（瑞士气象局））；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of Basel（巴塞尔大学）；Swisens AG（斯维森斯公司）
Peking University（北京大学）；Renmin University of China（中国人民大学）；Queen Mary University of London（伦敦玛丽女王大学）
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by learning a projection function between a feature space and a semantic space (e.g. attribute space). Considering the seen and unseen classes as two domains, a big domain gap often exists which challenges ZSL. Inspired by the fact that an unseen class is not exactly `unseen' if it belongs to the same superclass as a seen class, we propose a novel inductive ZSL model that leverages superclasses as the bridge between seen a…
Arizona State University（亚利桑那州立大学）；City University of Hong Kong（香港城市大学）
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommendation systems, E-commerce platforms, etc. can be represented by graph models. In this paper, we investigate the challenging yet practical problem, Graph Few-shot Class-incremental (Graph FCL) problem, where the graph model is tasked to classify both newly encountered classes and previously learned classes. Towards that purpose, we put forward a Graph Pseudo Incremental Learning paradigm by sampling tasks recurrently f…
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
Image-guided adaptive lung radiotherapy requires accurate tumor and organs segmentation from during treatment cone-beam CT (CBCT) images. Thoracic CBCTs are hard to segment because of low soft-tissue contrast, imaging artifacts, respiratory motion, and large treatment induced intra-thoracic anatomic changes. Hence, we developed a novel Patient-specific Anatomic Context and Shape prior or PACS-aware 3D recurrent registration-segmentation network for longitudinal thoracic CBCT segmentation. Segmentation and registration networks were concurrently trained in an end-to-end framework and implemente…
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task-owners susceptible to breaches of privacy. We conduct the first formal study of privacy in this setting and formalize the notion of task-global differential privacy as a practical relaxation of more commonly studied threat models. We then propose a new differentially private alg…
A new algorithmic framework is presented for holographic phase retrieval via maximum likelihood optimization, which allows for practical and robust image reconstruction. This framework is especially well-suited for holographic coherent diffraction imaging in the \textit{low-photon regime}, where data is highly corrupted by Poisson shot noise. Thus, this methodology provides a viable solution towards the advent of \textit{low-photon nanoscale imaging}, which is a fundamental challenge facing the current state of imaging technologies. Practical optimization algorithms are derived and implemented…
University of California, Los Angeles（加州大学洛杉矶分校）；California NanoSystems Institute（加州纳米系统研究所）；David Geffen School of Medicine（大卫·格芬医学院）
Polarized light microscopy provides high contrast to birefringent specimen and is widely used as a diagnostic tool in pathology. However, polarization microscopy systems typically operate by analyzing images collected from two or more light paths in different states of polarization, which lead to relatively complex optical designs, high system costs or experienced technicians being required. Here, we present a deep learning-based holographic polarization microscope that is capable of obtaining quantitative birefringence retardance and orientation information of specimen from a phase recovered …
A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
School of Information Engineering, Xi’an Eurasia University, Xi’an, 710065, Shaanxi, China（西安欧亚大学信息工程学院）；Department of Electrical Engineering, University of Engineering and Technology Lahore（拉合尔工程与技术大学电气工程系）；Department of Computer Science, University of Engineering and Technology Lahore（拉合尔工程与技术大学计算机科学系）
Multi-spectral quantitative phase imaging (MS-QPI) is a cutting-edge label-free technique to determine the morphological changes, refractive index variations and spectroscopic information of the specimens. The bottleneck to implement this technique to extract quantitative information, is the need of more than two measurements for generating MS-QPI images. We propose a single-shot MS-QPI technique using highly spatially sensitive digital holographic microscope assisted with deep neural network (DNN). Our method first acquires the interferometric datasets corresponding to multiple wavelengths (λ…
