The challenge of learning a new concept, object, or a new medical disease recognition without receiving any examples beforehand is called Zero-Shot Learning (ZSL). One of the major issues in deep learning based methodologies such as in Medical Imaging and other real-world applications is the requirement of large annotated datasets prepared by clinicians or experts to train the model. ZSL is known for having minimal human intervention by relying only on previously known or trained concepts plus currently existing auxiliary information. This makes the ZSL applicable in many real-world scenarios, from unknown object detection in autonomous vehicles to medical imaging and unforeseen diseases such as COVID-19 Chest X-Ray (CXR) based diagnosis. We introduce a novel and broaden solution called Few/one-shot learning, and present the definition of the ZSL problem as an extreme case of the few-shot learning. We review over fundamentals and the challenging steps of Zero-Shot Learning, including state-of-the-art categories of solutions, as well as our recommended solution, motivations behind each approach, their advantages over each category to guide both clinicians and AI researchers to proceed with the best techniques and practices based on their applications. We then review through different datasets inducing medical and non-medical images, the variety of splits, and the evaluation protocols proposed so far. Finally, we discuss the recent applications and future directions of ZSL. We aim to convey a useful intuition through this paper towards the goal of handling complex learning tasks more similar to the way humans learn. We mainly focus on two applications in the current modern yet challenging era: coping with an early and fast diagnosis of COVID-19 cases, and also encouraging the readers to develop other similar AI-based automated detection/recognition systems using ZSL.
Video Object Segmentation (VOS) is an active research area of the visual domain. One of its fundamental sub-tasks is semi-supervised / one-shot learning: given only the segmentation mask for the first frame, the task is to provide pixel-accurate masks for the object over the rest of the sequence. Despite much progress in the last years, we noticed that many of the existing approaches lose objects in longer sequences, especially when the object is small or briefly occluded. In this work, we build upon a sequence-to-sequence approach that employs an encoder-decoder architecture together with a memory module for exploiting the sequential data. We further improve this approach by proposing a model that manipulates multi-scale spatio-temporal information using memory-equipped skip connections. Furthermore, we incorporate an auxiliary task based on distance classification which greatly enhances the quality of edges in segmentation masks. We compare our approach to the state of the art and show considerable improvement in the contour accuracy metric and the overall segmentation accuracy.
Type inference over partial contexts in dynamically typed languages is challenging. In this work, we present a graph neural network model that predicts types by probabilistically reasoning over a program's structure, names, and patterns. The network uses deep similarity learning to learn a TypeSpace -- a continuous relaxation of the discrete space of types -- and how to embed the type properties of a symbol (i.e. identifier) into it. Importantly, our model can employ one-shot learning to predict an open vocabulary of types, including rare and user-defined ones. We realise our approach in Typilus for Python that combines the TypeSpace with an optional type checker. We show that Typilus accurately predicts types. Typilus confidently predicts types for 70% of all annotatable symbols; when it predicts a type, that type optionally type checks 95% of the time. Typilus can also find incorrect type annotations; two important and popular open source libraries, fairseq and allennlp, accepted our pull requests that fixed the annotation errors Typilus discovered.
We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance and is skilled at solving a specific type of learning problem. The meta-meta classifier learns how to examine a given learning problem and combine the various learners to solve the problem. The meta-meta learning approach is especially suited to solving few-shot learning tasks, as it is easier to learn to classify a new learning problem with little data than it is to apply a learning algorithm to a small data set. We evaluate the approach on a one-shot, one-class-versus-all classification task and show that it is able to outperform traditional meta-learning as well as ensembling approaches.
Fake face detection is a significant challenge for intelligent systems as generative models become more powerful every single day. As the quality of fake faces increases, the trained models become more and more inefficient to detect the novel fake faces, since the corresponding training data is considered outdated. In this case, robust One-Shot learning methods is more compatible with the requirements of changeable training data. In this paper, we propose a universal One-Shot GAN generated fake face detection method which can be used in significantly different areas of anomaly detection. The proposed method is based on extracting out-of-context objects from faces via scene understanding models. To do so, we use state of the art scene understanding and object detection methods as a pre-processing tool to detect the weird objects in the face. Second, we create a bag of words given all the detected out-of-context objects per all training data. This way, we transform each image into a sparse vector where each feature represents the confidence score related to each detected object in the image. Our experiments show that, we can discriminate fake faces from real ones in terms of out-of-context features. It means that, different sets of objects are detected in fake faces comparing to real ones when we analyze them with scene understanding and object detection models. We prove that, the proposed method can outperform previous methods based on our experiments on Style-GAN generated fake faces.
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an embedding function f trained jointly with a "composition" function g that computes set union operations between the classes encoded in two embedding vectors; and (2) embedding f trained jointly with a "query" function h that computes whether the classes encoded in one embedding subsume the classes encoded in another embedding. In contrast to prior work, these models must both perceive the classes associated with the input examples and encode the relationships between different class label sets, and they are trained using only weak one-shot supervision consisting of the label-set relationships among training examples. Experiments on the OmniGlot, Open Images, and COCO datasets show that the proposed compositional embedding models outperform existing embedding methods. Our compositional embedding models have applications to multi-label object recognition for both one-shot and supervised learning.
The creation of machine learning algorithms for intelligent agents capable of continuous, lifelong learning is a critical objective for algorithms being deployed on real-life systems in dynamic environments. Here we present an algorithm inspired by neuromodulatory mechanisms in the human brain that integrates and expands upon Stephen Grossberg\'s ground-breaking Adaptive Resonance Theory proposals. Specifically, it builds on the concept of uncertainty, and employs a series of neuromodulatory mechanisms to enable continuous learning, including self-supervised and one-shot learning. Algorithm components were evaluated in a series of benchmark experiments that demonstrate stable learning without catastrophic forgetting. We also demonstrate the critical role of developing these systems in a closed-loop manner where the environment and the agent\'s behaviors constrain and guide the learning process. To this end, we integrated the algorithm into an embodied simulated drone agent. The experiments show that the algorithm is capable of continuous learning of new tasks and under changed conditions with high classification accuracy (greater than 94 percent) in a virtual environment, without catastrophic forgetting. The algorithm accepts high dimensional inputs from any state-of-the-art detection and feature extraction algorithms, making it a flexible addition to existing systems. We also describe future development efforts focused on imbuing the algorithm with mechanisms to seek out new knowledge as well as employ a broader range of neuromodulatory processes.
Myocardial infarction (MI) is a scientific term that refers to heart attack. In this study, we infer highly relevant second harmonic generation (SHG) cues from collagen fibers exhibiting highly non-centrosymmetric assembly together with two-photon excited cellular autofluorescence in infarcted mouse heart to quantitatively probe fibrosis, especially targeted at an early stage after MI. We present a robust one-shot machine learning algorithm that enables determination of 2D assembly of collagen with high spatial resolution along with its structural arrangement in heart tissues post-MI with spectral specificity and sensitivity. Detection, evaluation, and precise quantification of fibrosis extent at early stage would guide one to develop treatment therapies that may prevent further progression and determine heart transplant needs for patient survival.
People are becoming increasingly comfortable using Digital Assistants (DAs) to interact with services or connected objects. However, for non-programming users, the available possibilities for customizing their DA are limited and do not include the possibility of teaching the assistant new tasks. To make the most of the potential of DAs, users should be able to customize assistants by instructing them through Natural Language (NL). To provide such functionalities, NL interpretation in traditional assistants should be improved: (1) The intent identification system should be able to recognize new forms of known intents, and to acquire new intents as they are expressed by the user. (2) In order to be adaptive to novel intents, the Natural Language Understanding module should be sample efficient, and should not rely on a pretrained model. Rather, the system should continuously collect the training data as it learns new intents from the user. In this work, we propose AidMe (Adaptive Intent Detection in Multi-Domain Environments), a user-in-the-loop adaptive intent detection framework that allows the assistant to adapt to its user by learning his intents as their interaction progresses. AidMe builds its repertoire of intents and collects data to train a model of semantic similarity evaluation that can discriminate between the learned intents and autonomously discover new forms of known intents. AidMe addresses two major issues - intent learning and user adaptation - for instructable digital assistants. We demonstrate the capabilities of AidMe as a standalone system by comparing it with a one-shot learning system and a pretrained NLU module through simulations of interactions with a user. We also show how AidMe can smoothly integrate to an existing instructable digital assistant.
Defining similarity measures is a requirement for some machine learning methods. One such method is case-based reasoning (CBR) where the similarity measure is used to retrieve the stored case or set of cases most similar to the query case. Describing a similarity measure analytically is challenging, even for domain experts working with CBR experts. However, data sets are typically gathered as part of constructing a CBR or machine learning system. These datasets are assumed to contain the features that correctly identify the solution from the problem features, thus they may also contain the knowledge to construct or learn such a similarity measure. The main motivation for this work is to automate the construction of similarity measures using machine learning, while keeping training time as low as possible. Our objective is to investigate how to apply machine learning to effectively learn a similarity measure. Such a learned similarity measure could be used for CBR systems, but also for clustering data in semi-supervised learning, or one-shot learning tasks. Recent work has advanced towards this goal, relies on either very long training times or manually modeling parts of the similarity measure. We created a framework to help us analyze current methods for learning similarity measures. This analysis resulted in two novel similarity measure designs. One design using a pre-trained classifier as basis for a similarity measure. The second design uses as little modeling as possible while learning the similarity measure from data and keeping training time low. Both similarity measures were evaluated on 14 different datasets. The evaluation shows that using a classifier as basis for a similarity measure gives state of the art performance. Finally the evaluation shows that our fully data-driven similarity measure design outperforms state of the art methods while keeping training time low.
Recent advances show that Neural Architectural Search (NAS) method is able to find state-of-the-art image classification deep architectures. In this paper, we consider the one-shot NAS problem for resource constrained applications. This problem is of great interest because it is critical to choose different architectures according to task complexity when the resource is constrained. Previous techniques are either too slow for one-shot learning or does not take the resource constraint into consideration. In this paper, we propose the resource constrained differentiable architecture search (RC-DARTS) method to learn architectures that are significantly smaller and faster while achieving comparable accuracy. Specifically, we propose to formulate the RC-DARTS task as a constrained optimization problem by adding the resource constraint. An iterative projection method is proposed to solve the given constrained optimization problem. We also propose a multi-level search strategy to enable layers at different depths to adaptively learn different types of neural architectures. Through extensive experiments on the Cifar10 and ImageNet datasets, we show that the RC-DARTS method learns lightweight neural architectures which have smaller model size and lower computational complexity while achieving comparable or better performances than the state-of-the-art methods.
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art.
Home robots may come with many sophisticated built-in abilities, however there will always be a degree of customization needed for each user and environment. Ideally this should be accomplished through one-shot learning, as collecting the large number of examples needed for statistical inference is tedious. A particularly appealing approach is to simply explain to the robot, via speech, what it should be doing. In this paper we describe the ALIA cognitive architecture that is able to effectively incorporate user-supplied advice and prohibitions in this manner. The functioning of the implemented system on a small robot is illustrated by an associated video.
One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize additional training images, but these synthesized images are often not helpful for actually improving the accuracy of one-shot fine-grained recognition. This paper proposes a meta-learning framework to combine generated images with original images, so that the resulting ``hybrid'' training images can improve one-shot learning. Specifically, the generic image generator is updated by a few training instances of novel classes, and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. The model is trained in an end-to-end manner, and our experiments demonstrate consistent improvement over baselines on one-shot fine-grained image classification benchmarks.
The lack of a large amount of training data has always been the constraining factor in solving a lot of problems in machine learning, making One Shot Learning one of the most intriguing ideas in machine learning. It aims to learn information about object categories from one, or only a few training examples. This process of learning in deep learning is usually accomplished by proper objective function, i.e; loss function and embeddings extraction i.e; architecture. In this paper, we discussed about metrics based deep learning architectures for one shot learning such as Siamese neural networks and present a method to improve on their accuracy using Kafnets (kernel-based non-parametric activation functions for neural networks) by learning proper embeddings with relatively less number of epochs. Using kernel activation functions, we are able to achieve strong results which exceed those of ReLU based deep learning models in terms of embeddings structure, loss convergence, and accuracy.
One-shot face recognition measures the ability to identify persons with only seeing them at one glance, and is a hallmark of human visual intelligence. It is challenging for conventional machine learning approaches to mimic this way, since limited data are hard to effectively represent the data variance. The goal of one-shot face recognition is to learn a large-scale face recognizer, which is capable to fight off the data imbalance challenge. In this paper, we propose a novel generative adversarial one-shot face recognizer, attempting to synthesize meaningful data for one-shot classes by adapting the data variances from other normal classes. Specifically, we target at building a more effective general face classifier for both normal persons and one-shot persons. Technically, we design a new loss function by formulating knowledge transfer generator and a general classifier into a unified framework. Such a two-player minimax optimization can guide the generation of more effective data, which effectively promote the underrepresented classes in the learned model and lead to a remarkable improvement in face recognition performance. We evaluate our proposed model on the MS-Celeb-1M one-shot learning benchmark task, where we could recognize 94.98% of the test images at the precision of 99% for the one-shot classes, keeping an overall Top1 accuracy at $99.80\%$ for the normal classes. To the best of our knowledge, this is the best performance among all the published methods using this benchmark task with the same setup, including all the participants in the recent MS-Celeb-1M challenge at ICCV 2017\footnote{http://www.msceleb.org/challenge2/2017}.
We present an architecture for integrating real-time, multimodal input into a computational agent's contextual model. Using a human-avatar interaction in a virtual world, we treat aligned gesture and speech as an ensemble where content may be communicated by either modality. With a modified nondeterministic pushdown automaton architecture, the computer system: (1) consumes input incrementally using continuation-passing style until it achieves sufficient understanding the user's aim; (2) constructs and asks questions where necessary using established contextual information; and (3) maintains track of prior discourse items using multimodal cues. This type of architecture supports special cases of pushdown and finite state automata as well as integrating outputs from machine learning models. We present examples of this architecture's use in multimodal one-shot learning interactions of novel gestures and live action composition.
In this work we present Ludwig, a flexible, extensible and easy to use toolbox which allows users to train deep learning models and use them for obtaining predictions without writing code. Ludwig implements a novel approach to deep learning model building based on two main abstractions: data types and declarative configuration files. The data type abstraction allows for easier code and sub-model reuse, and the standardized interfaces imposed by this abstraction allow for encapsulation and make the code easy to extend. Declarative model definition configuration files enable inexperienced users to obtain effective models and increase the productivity of expert users. Alongside these two innovations, Ludwig introduces a general modularized deep learning architecture called Encoder-Combiner-Decoder that can be instantiated to perform a vast amount of machine learning tasks. These innovations make it possible for engineers, scientists from other fields and, in general, a much broader audience to adopt deep learning models for their tasks, concretely helping in its democratization.
We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that are mentioned in the text portion that is currently being read. The agent is expected to learn to follow the narrations, thus disambiguating mentions and discovering new individuals. We focus on the case in which individuals are entities and relations, and we propose an end-to-end trainable memory network that learns to discover and disambiguate them in an online manner, performing one-shot learning, and dealing with a small number of sparse supervisions. Our system builds a not-given-in-advance knowledge base, and it improves its skills while reading unsupervised text. The model deals with abrupt changes in the narration, taking into account their effects when resolving co-references. We showcase the strong disambiguation and discovery skills of our model on a corpus of Wikipedia documents and on a newly introduced dataset, that we make publicly available.
One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are continuously made available to the learner that have to decide whether to request a label or to make a prediction. The goal is to reduce the request rate while at the same time maximize prediction performance. In previous research, reinforcement learning has been used for learning the AL request/prediction strategy. In our work, we propose to equip a reinforcement learning process with memory augmented neural networks, to enhance the one-shot capabilities. Moreover, we introduce Class Margin Sampling (CMS) as an extension of the standard margin sampling to the reinforcement learning setting. This strategy aims to reduce training time and improve sample efficiency in the training process. We evaluate the proposed method on a classification task using empirical accuracy of label predictions and percentage of label requests. The results indicates that the proposed method, by making use of the memory augmented networks and CMS in the training process, outperforms existing baselines.