It is well established that training deep neural networks gives useful representations that capture essential features of the inputs. However, these representations are poorly understood in theory and practice. In the context of supervised learning an important question is whether these representations capture features informative for classification, while filtering out non-informative noisy ones. We explore a formalization of this question by considering a generative process where each class is associated with a high-dimensional manifold and different classes define different manifolds. Under this model, each input is produced using two latent vectors: (i) a "manifold identifier" $\gamma$ and; (ii)~a "transformation parameter" $\theta$ that shifts examples along the surface of a manifold. E.g., $\gamma$ might represent a canonical image of a dog, and $\theta$ might stand for variations in pose, background or lighting. We provide theoretical and empirical evidence that neural representations can be viewed as LSH-like functions that map each input to an embedding that is a function of solely the informative $\gamma$ and invariant to $\theta$, effectively recovering the manifold identifier $\gamma$. An important consequence of this behavior is one-shot learning to unseen classes.
For the task of face verification, we explore the utility of harnessing auxiliary facial emotion labels to impose explicit geometric constraints on the embedding space when training deep embedding models. We introduce several novel loss functions that, in conjunction with a standard Triplet Loss [43], or ArcFace loss [10], provide geometric constraints on the embedding space; the labels for our loss functions can be provided using either manually annotated or automatically detected auxiliary emotion labels. Our method is implemented purely in terms of the loss function and does not require any changes to the neural network backbone of the embedding function.
Increasingly large datasets are rapidly driving up the computational costs of machine learning. Prototype generation methods aim to create a small set of synthetic observations that accurately represent a training dataset but greatly reduce the computational cost of learning from it. Assigning soft labels to prototypes can allow increasingly small sets of prototypes to accurately represent the original training dataset. Although foundational work on `less than one'-shot learning has proven the theoretical plausibility of learning with fewer than one observation per class, developing practical algorithms for generating such prototypes remains an unexplored territory. We propose a novel, modular method for generating soft-label prototypical lines that still maintains representational accuracy even when there are fewer prototypes than the number of classes in the data. In addition, we propose the Hierarchical Soft-Label Prototype k-Nearest Neighbor classification algorithm based on these prototypical lines. We show that our method maintains high classification accuracy while greatly reducing the number of prototypes required to represent a dataset, even when working with severely imbalanced and difficult data. Our code is available at https://github.com/ilia10000/SLkNN.
Standard few-shot experiments involve learning to efficiently match previously unseen samples by class. We claim that few-shot learning should be long term, assimilating knowledge for the future, without forgetting previous concepts. In the mammalian brain, the hippocampus is understood to play a significant role in this process, by learning rapidly and consolidating knowledge to the neocortex incrementally over a short period. In this research we tested whether an artificial hippocampal algorithm (AHA), could be used with a conventional Machine Learning (ML) model that learns incrementally analogous to the neocortex, to achieve one-shot learning both short and long term. The results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting. This study is one of the first examples of using a CLS model of hippocampus to consolidate memories, and it constitutes a step toward few-shot continual learning.
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation, bilingual dictionaries are a promising knowledge source to continuously integrate new knowledge. However, their exploitation poses several challenges: The system needs to be able to perform one-shot learning as well as model the morphology of source and target language. In this work, we proposed an evaluation framework to assess the ability of neural machine translation to continuously learn new phrases. We integrate one-shot learning methods for neural machine translation with different word representations and show that it is important to address both in order to successfully make use of bilingual dictionaries. By addressing both challenges we are able to improve the ability to translate new, rare words and phrases from 30% to up to 70%. The correct lemma is even generated by more than 90%.
In echocardiography (echo), an electrocardiogram (ECG) is conventionally used to temporally align different cardiac views for assessing critical measurements. However, in emergencies or point-of-care situations, acquiring an ECG is often not an option, hence motivating the need for alternative temporal synchronization methods. Here, we propose Echo-SyncNet, a self-supervised learning framework to synchronize various cross-sectional 2D echo series without any external input. The proposed framework takes advantage of both intra-view and inter-view self supervisions. The former relies on spatiotemporal patterns found between the frames of a single echo cine and the latter on the interdependencies between multiple cines. The combined supervisions are used to learn a feature-rich embedding space where multiple echo cines can be temporally synchronized. We evaluate the framework with multiple experiments: 1) Using data from 998 patients, Echo-SyncNet shows promising results for synchronizing Apical 2 chamber and Apical 4 chamber cardiac views; 2) Using data from 3070 patients, our experiments reveal that the learned representations of Echo-SyncNet outperform a supervised deep learning method that is optimized for automatic detection of fine-grained cardiac phase; 3) We show the usefulness of the learned representations in a one-shot learning scenario of cardiac keyframe detection. Without any fine-tuning, keyframes in 1188 validation patient studies are identified by synchronizing them with only one labeled reference study. We do not make any prior assumption about what specific cardiac views are used for training and show that Echo-SyncNet can accurately generalize to views not present in its training set. Project repository: github.com/fatemehtd/Echo-SyncNet.
Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their scalability and usability in large scale deployments. In this work, we present a novel selective tracklet learning (STL) approach that can train discriminative person re-id models from unlabelled tracklet data in an unsupervised manner. This avoids the tedious and costly process of exhaustively labelling person image/tracklet true matching pairs across camera views. Importantly, our method is particularly more robust against arbitrary noisy data of raw tracklets therefore scalable to learning discriminative models from unconstrained tracking data. This differs from a handful of existing alternative methods that often assume the existence of true matches and balanced tracklet samples per identity class. This is achieved by formulating a data adaptive image-to-tracklet selective matching loss function explored in a multi-camera multi-task deep learning model structure. Extensive comparative experiments demonstrate that the proposed STL model surpasses significantly the state-of-the-art unsupervised learning and one-shot learning re-id methods on three large tracklet person re-id benchmarks.
Audio to Video generation is an interesting problem that has numerous applications across industry verticals including film making, multi-media, marketing, education and others. High-quality video generation with expressive facial movements is a challenging problem that involves complex learning steps for generative adversarial networks. Further, enabling one-shot learning for an unseen single image increases the complexity of the problem while simultaneously making it more applicable to practical scenarios. In the paper, we propose a novel approach OneShotA2V to synthesize a talking person video of arbitrary length using as input: an audio signal and a single unseen image of a person. OneShotA2V leverages curriculum learning to learn movements of expressive facial components and hence generates a high-quality talking-head video of the given person. Further, it feeds the features generated from the audio input directly into a generative adversarial network and it adapts to any given unseen selfie by applying fewshot learning with only a few output updation epochs. OneShotA2V leverages spatially adaptive normalization based multi-level generator and multiple multi-level discriminators based architecture. The input audio clip is not restricted to any specific language, which gives the method multilingual applicability. Experimental evaluation demonstrates superior performance of OneShotA2V as compared to Realistic Speech-Driven Facial Animation with GANs(RSDGAN) [43], Speech2Vid [8], and other approaches, on multiple quantitative metrics including: SSIM (structural similarity index), PSNR (peak signal to noise ratio) and CPBD (image sharpness). Further, qualitative evaluation and Online Turing tests demonstrate the efficacy of our approach.
Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification. In our research, we focused on two tasks related to vegetation. The first one is plant disease detection on 25 classes of five crops (grape, cotton, wheat, cucumbers, and corn). This task is motivated because harvest losses due to diseases is a serious problem for both large farming structures and rural families. The second task is the identification of moss species (5 classes). Mosses are natural bioaccumulators of pollutants; therefore, they are used in environmental monitoring programs. The identification of moss species is an important step in the sample preprocessing. In both tasks, we used self-collected image databases. We tried several deep learning architectures and approaches. Our Siamese network architecture with a triplet loss function and MobileNetV2 as a base network showed the most impressive results in both above-mentioned tasks. The average accuracy for plant disease detection amounted to over 97.8% and 97.6% for moss species classification.
Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-efficient methods that permit to produce accurate anatomical structure segmentation are highly desirable. In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. We formulate anatomy segmentation as a contour evolution process and model the evolution behavior by graph convolutional networks (GCNs). Training the CTN model requires only one labeled image exemplar and leverages additional unlabeled data through newly introduced loss functions that measure the global shape and appearance consistency of contours. On segmentation tasks of four different anatomies, we demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.
In many daily tasks we make multiple decisions before reaching a goal. In order to learn such sequences of decisions, a mechanism to link earlier actions to later reward is necessary. Reinforcement learning theory suggests two classes of algorithms solving this credit assignment problem: In classic temporal-difference learning, earlier actions receive reward information only after multiple repetitions of the task, whereas models with eligibility traces reinforce entire sequences of actions from a single experience (one-shot). Here we asked whether humans use eligibility traces. We developed a novel paradigm to directly observe which actions and states along a multi-step sequence are reinforced after a single reward. By focusing our analysis on those states for which RL with and without eligibility trace make qualitatively distinct predictions, we find direct behavioral (choice probability) and physiological (pupil dilation) signatures of reinforcement learning with eligibility trace across multiple sensory modalities.
Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neural architecture Search(NAS) for each task to tackle this challenge. However, existing works impose significant limitations on the design or search space. To solve these problems, we present ScaleNAS, a one-shot learning method for exploring scale-aware representations. ScaleNAS solves multiple tasks at a time by searching multi-scale feature aggregation. ScaleNAS adopts a flexible search space that allows an arbitrary number of blocks and cross-scale feature fusions. To cope with the high search cost incurred by the flexible space, ScaleNAS employs one-shot learning for multi-scale supernet driven by grouped sampling and evolutionary search. Without further retraining, ScaleNet can be directly deployed for different visual recognition tasks with superior performance. We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation. ScaleNet-P and ScaleNet-S outperform existing manually crafted and NAS-based methods in both tasks. When applying ScaleNet-P to bottom-up human pose estimation, it surpasses the state-of-the-art HigherHRNet. In particular, ScaleNet-P4 achieves 71.6% AP on COCO test-dev, achieving new state-of-the-art result.
Preliminary detection of mild depression could immensely help in effective treatment of the common mental health disorder. Due to the lack of proper awareness and the ample mix of stigmas and misconceptions present within the society, mental health status estimation has become a truly difficult task. Due to the immense variations in character level traits from person to person, traditional deep learning methods fail to generalize in a real world setting. In our study we aim to create a human allied AI workflow which could efficiently adapt to specific users and effectively perform in real world scenarios. We propose a Hybrid deep learning approach that combines the essence of one shot learning, classical supervised deep learning methods and human allied interactions for adaptation. In order to capture maximum information and make efficient diagnosis video, audio, and text modalities are utilized. Our Hybrid Fusion model achieved a high accuracy of 96.3% on the Dataset; and attained an AUC of 0.9682 which proves its robustness in discriminating classes in complex real-world scenarios making sure that no cases of mild depression are missed during diagnosis. The proposed method is deployed in a cloud-based smartphone application for robust testing. With user-specific adaptations and state of the art methodologies, we present a state-of-the-art model with user friendly experience.
The automation of document processing is gaining recent attention due to the great potential to reduce manual work through improved methods and hardware. Neural networks have been successfully applied before - even though they have been trained only on relatively small datasets with hundreds of documents so far. To successfully explore deep learning techniques and improve the information extraction results, a dataset with more than twenty-five thousand documents has been compiled, anonymized and is published as a part of this work. We will expand our previous work where we proved that convolutions, graph convolutions and self-attention can work together and exploit all the information present in a structured document. Taking the fully trainable method one step further, we will now design and examine various approaches to using siamese networks, concepts of similarity, one-shot learning and context/memory awareness. The aim is to improve micro F1 of per-word classification on the huge real-world document dataset. The results verify the hypothesis that trainable access to a similar (yet still different) page together with its already known target information improves the information extraction. Furthermore, the experiments confirm that all proposed architecture parts are all required to beat the previous results. The best model improves the previous state-of-the-art results by an 8.25 gain in F1 score. Qualitative analysis is provided to verify that the new model performs better for all target classes. Additionally, multiple structural observations about the causes of the underperformance of some architectures are revealed. All the source codes, parameters and implementation details are published together with the dataset in the hope to push the research boundaries since all the techniques used in this work are not problem-specific and can be generalized for other tasks and contexts.
This paper presents methods to identify the plastic waste based on its resin identification code to provide an efficient recycling of post-consumer plastic waste. We propose the design, training and testing of different machine learning techniques to (i) identify a plastic waste that belongs to the known categories of plastic waste when the system is trained and (ii) identify a new plastic waste that do not belong the any known categories of plastic waste while the system is trained. For the first case,we propose the use of one-shot learning techniques using Siamese and Triplet loss networks. Our proposed approach does not require any augmentation to increase the size of the database and achieved a high accuracy of 99.74%. For the second case, we propose the use of supervised and unsupervised dimensionality reduction techniques and achieved an accuracy of 95% to correctly identify a new plastic waste.
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ. Using a single representative dialog from the restaurant domain, we train DILOG on the SimDial dataset and obtain 99+% in-domain test accuracy. We also show that the trained DILOG zero-shot transfers to all other domains with 99+% accuracy, proving the suitability of DILOG to slot-filling dialogs. We further extend our study to the MultiWoZ dataset achieving 90+% inform and success metrics. We also observe that these metrics are not capturing some of the shortcomings of DILOG in terms of false positives, prompting us to measure an auxiliary Action F1 score. We show that DILOG is 100x more data efficient than state-of-the-art neural approaches on MultiWoZ while achieving similar performance metrics. We conclude with a discussion on the strengths and weaknesses of DILOG.
Being very low power, the use of neuromorphic processors in mobile devices to solve machine learning problems is a promising alternative to traditional Von Neumann processors. Federated Learning enables entities such as mobile devices to collaboratively learn a shared model while keeping their training data local. Additionally, federated learning is a secure way of learning because only the model weights need to be shared between models, keeping the data private. Here we demonstrate the efficacy of federated learning in neuromorphic processors. Neuromorphic processors benefit from the collaborative learning, achieving state of the art accuracy on a one-shot learning gesture recognition task across individual processor models while preserving local data privacy.
Established experimental procedures for one-shot machine learning do not test the ability to learn or remember specific instances of classes, a key feature of animal intelligence. Distinguishing specific instances is necessary for many real-world tasks, such as remembering which cup belongs to you. Generalisation within classes conflicts with the ability to separate instances of classes, making it difficult to achieve both capabilities within a single architecture. We propose an extension to the standard Omniglot classification-generalisation framework that additionally tests the ability to distinguish specific instances after one exposure and introduces noise and occlusion corruption. Learning is defined as an ability to classify as well as recall training samples. Complementary Learning Systems (CLS) is a popular model of mammalian brain regions believed to play a crucial role in learning from a single exposure to a stimulus. We created an artificial neural network implementation of CLS and applied it to the extended Omniglot benchmark. Our unsupervised model demonstrates comparable performance to existing supervised ANNs on the Omniglot classification task (requiring generalisation), without the need for domain-specific inductive biases. On the extended Omniglot instance-recognition task, the same model also demonstrates significantly better performance than a baseline nearest-neighbour approach, given partial occlusion and noise.
Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times. This observation has given rise to recent interest in low-shot learning methods that are able to generalize from only a few examples. The existing approaches, however, are tailored to static knowledge graphs and not easily generalized to temporal settings, where data scarcity poses even bigger problems, e.g., due to occurrence of new, previously unseen relations. We address this shortcoming by proposing a one-shot learning framework for link prediction in temporal knowledge graphs. Our proposed method employs a self-attention mechanism to effectively encode temporal interactions between entities, and a network to compute a similarity score between a given query and a (one-shot) example. Our experiments show that the proposed algorithm outperforms the state of the art baselines for two well-studied benchmarks while achieving significantly better performance for sparse relations.
Image contour based vision measurement is widely applied in robot manipulation and industrial automation. It is appealing to realize object-agnostic vision system, which can be conveniently reused for various types of objects. We propose the contour primitive of interest extraction network (CPieNet) based on the one-shot learning framework. First, CPieNet is featured by that its contour primitive of interest (CPI) output, a designated regular contour part lying on a specified object, provides the essential geometric information for vision measurement. Second, CPieNet has the one-shot learning ability, utilizing a support sample to assist the perception of the novel object. To realize lower-cost training, we generate support-query sample pairs from unpaired online public images, which cover a wide range of object categories. To obtain single-pixel wide contour for precise measurement, the Gabor-filters based non-maximum suppression is designed to thin the raw contour. For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot. The effectiveness of the proposed methods is validated by a series of experiments.