In most existing learning systems, images are typically viewed as 2D pixel arrays. However, in another paradigm gaining popularity, a 2D image is represented as an implicit neural representation (INR) -- an MLP that predicts an RGB pixel value given its (x,y) coordinate. In this paper, we propose two novel architectural techniques for building INR-based image decoders: factorized multiplicative modulation and multi-scale INRs, and use them to build a state-of-the-art continuous image GAN. Previous attempts to adapt INRs for image generation were limited to MNIST-like datasets and do not scale to complex real-world data. Our proposed architectural design improves the performance of continuous image generators by x6-40 times and reaches FID scores of 6.27 on LSUN bedroom 256x256 and 16.32 on FFHQ 1024x1024, greatly reducing the gap between continuous image GANs and pixel-based ones. To the best of our knowledge, these are the highest reported scores for an image generator, that consists entirely of fully-connected layers. Apart from that, we explore several exciting properties of INR-based decoders, like out-of-the-box superresolution, meaningful image-space interpolation, accelerated inference of low-resolution images, an ability to extrapolate outside of image boundaries and strong geometric prior. The source code is available at https://github.com/universome/inr-gan

We introduce Inner Ensemble Networks (IENs) which reduce the variance within the neural network itself without an increase in the model complexity. IENs utilize ensemble parameters during the training phase to reduce the network variance. While in the testing phase, these parameters are removed without a change in the enhanced performance. IENs reduce the variance of an ordinary deep model by a factor of $1/m^{L-1}$, where $m$ is the number of inner ensembles and $L$ is the depth of the model. Also, we show empirically and theoretically that IENs lead to a greater variance reduction in comparison with other similar approaches such as dropout and maxout. Our results show a decrease of error rates between 1.7\% and 17.3\% in comparison with an ordinary deep model. We also show that IEN was preferred by Neural Architecture Search (NAS) methods over prior approaches. Code is available at https://github.com/abduallahmohamed/inner_ensemble_nets.

Understanding the relationships between biomedical terms like viruses, drugs, and symptoms is essential in the fight against diseases. Many attempts have been made to introduce the use of machine learning to the scientific process of hypothesis generation (HG), which refers to the discovery of meaningful implicit connections between biomedical terms. However, most existing methods fail to truly capture the temporal dynamics of scientific term relations and also assume unobserved connections to be irrelevant (i.e., in a positive-negative (PN) learning setting). To break these limits, we formulate this HG problem as future connectivity prediction task on a dynamic attributed graph via positive-unlabeled (PU) learning. Then, the key is to capture the temporal evolution of node pair (term pair) relations from just the positive and unlabeled data. We propose a variational inference model to estimate the positive prior, and incorporate it in the learning of node pair embeddings, which are then used for link prediction. Experiment results on real-world biomedical term relationship datasets and case study analyses on a COVID-19 dataset validate the effectiveness of the proposed model.

An ability to grasp new concepts from their descriptions is one of the key features of human intelligence, and zero-shot learning (ZSL) aims to incorporate this property into machine learning models. In this paper, we theoretically investigate two very popular tricks used in ZSL: "normalize scale" trick and attributes normalization and show how they help to preserve a signal's variance in a typical model during a forward pass. Next, we demonstrate that these two tricks are not enough to normalize a deep ZSL network. We derive a new initialization scheme, which allows us to demonstrate strong state-of-the-art results on 4 out of 5 commonly used ZSL datasets: SUN, CUB, AwA1, and AwA2 while being on average 2 orders faster than the closest runner-up. Finally, we generalize ZSL to a broader problem -- Continual Zero-Shot Learning (CZSL) and test our ideas in this new setup. The source code to reproduce all the results is available at https://github.com/universome/czsl.

Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' importance. In contrast, we propose Uncertainty-guided Continual Bayesian Neural Networks (UCB), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. Uncertainty is a natural way to identify what to remember and what to change as we continually learn, allowing to mitigate catastrophic forgetting. We also show a variant of our model, which uses uncertainty for weight pruning and retains task performance after pruning by saving binary masks per tasks. We evaluate our UCB approach extensively on diverse object classification datasets with short and long sequences of tasks and report superior or on-par performance compared to existing approaches. Additionally, we show that our model does not necessarily need task information at test time, i.e. it does not presume knowledge of which task a sample belongs to.

Learning with less supervision is a major challenge in artificial intelligence. One sensible approach to decrease the amount of supervision is to leverage prior experience and transfer knowledge from tasks seen in the past. However, a necessary condition for a successful transfer is the ability to remember how to perform previous tasks. The Continual Learning (CL) setting, whereby an agent learns from a stream of tasks without seeing any example twice, is an ideal framework to investigate how to accrue such knowledge. In this work, we consider supervised learning tasks and methods that leverage a very small episodic memory for continual learning. Through an extensive empirical analysis across four benchmark datasets adapted to CL, we observe that a very simple baseline, which jointly trains on both examples from the current task as well as examples stored in the memory, outperforms state-of-the-art CL approaches with and without episodic memory. Surprisingly, repeated learning over tiny episodic memories does not harm generalization on past tasks, as joint training on data from subsequent tasks acts like a data dependent regularizer. We discuss and evaluate different approaches to write into the memory. Most notably, reservoir sampling works remarkably well across the board, except when the memory size is extremely small. In this case, writing strategies that guarantee an equal representation of all classes work better. Overall, these methods should be considered as a strong baseline candidate when benchmarking new CL approaches

Learning from a few examples is a key characteristic of human intelligence that AI researchers have been excited about modeling. With the web-scale data being mostly unlabeled, few recent works showed that few-shot learning performance can be significantly improved with access to unlabeled data, known as semi-supervised few shot learning (SS-FSL). We introduce a SS-FSL approach that we denote as Consistent Prototypical Networks (CPN), which builds on top of Prototypical Networks. We propose new loss terms to leverage unlabelled data, by enforcing notions of local and global consistency. Our work shows the effectiveness of our consistency losses in semi-supervised few shot setting. Our model outperforms the state-of-the-art in most benchmarks, showing large improvements in some cases. For example, in one mini-Imagenet 5-shot classification task, we obtain 70.1% accuracy to the 64.59% state-of-the-art. Moreover, our semi-supervised model, trained with 40% of the labels, compares well against the vanilla prototypical network trained on 100% of the labels, even outperforming it in the 1-shot mini-Imagenet case with 51.03% to 49.4% accuracy. For reproducibility, we make our code publicly available.

Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images. An essential characteristic of generative models is their ability to produce multi-modal outputs. However, while training, they are often susceptible to mode collapse, that is models are limited in mapping input noise to only a few modes of the true data distribution. In this work, we draw inspiration from Determinantal Point Process (DPP) to propose an unsupervised penalty loss that alleviates mode collapse while producing higher quality samples. DPP is an elegant probabilistic measure used to model negative correlations within a subset and hence quantify its diversity. We use DPP kernel to model the diversity in real data as well as in synthetic data. Then, we devise an objective term that encourages generator to synthesize data with a similar diversity to real data. In contrast to previous state-of-the-art generative models that tend to use additional trainable parameters or complex training paradigms, our method does not change the original training scheme. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelebA, while outperforming state-of-the-art methods for data-efficiency, generation quality, and convergence-time whereas being 5.8x faster than its closest competitor.

In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, we introduce a new metric measuring how quickly a learner acquires a new skill. Third, we propose an improved version of GEM (Lopez-Paz & Ranzato, 2017), dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC (Kirkpatrick et al., 2016) and other regularization-based methods. Finally, we show that all algorithms including A-GEM can learn even more quickly if they are provided with task descriptors specifying the classification tasks under consideration. Our experiments on several standard lifelong learning benchmarks demonstrate that A-GEM has the best trade-off between accuracy and efficiency.

Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost creativity in fashion generation. The dimensions of our explorations include: (i) different Generative Adversarial Networks architectures that start from noise vectors to generate fashion items, (ii) a new loss function that encourages creativity, and (iii) a generation process following the key elements of fashion design (disentangling shape and texture makers). A key challenge of this study is the evaluation of generated designs and the retrieval of best ones, hence we put together an evaluation protocol associating automatic metrics and human experimental studies that we hope will help ease future research. We show that our proposed creativity loss yields better overall appreciation than the one employed in Creative Adversarial Networks. In the end, about 61% of our images are thought to be created by human designers rather than by a computer while also being considered original per our human subject experiments, and our proposed loss scores the highest compared to existing losses in both novelty and likability.