Related papers: A General Purpose Supervisory Signal for Embodied …

Object goal navigation is an important problem in Embodied AI that involves guiding the agent to navigate to an instance of the object category in an unknown environment -- typically an indoor scene. Unfortunately, current state-of-the-art…

In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the unsupervised image-to-image…

Industrial image anomaly detection under the setting of one-class classification has significant practical value. However, most existing models struggle to extract separable feature representations when performing feature embedding and…

Collecting operationally realistic data to inform machine learning models can be costly. Before collecting new data, it is helpful to understand where a model is deficient. For example, object detectors trained on images of rare objects may…

It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation"…

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired…

We introduce a new method for generating color images from sketches or edge maps. Current methods either require some form of additional user-guidance or are limited to the "paired" translation approach. We argue that segmentation…

Graph classification is a widely studied problem and has broad applications. In many real-world problems, the number of labeled graphs available for training classification models is limited, which renders these models prone to overfitting.…

Today's state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the actions of the agent taken in response to…

With great progress in the development of Generative Adversarial Networks (GANs), in recent years, the quest for insights in understanding and manipulating the latent space of GAN has gained more and more attention due to its wide range of…

Decoding visual neural representations from Electroencephalography (EEG) signals remains a formidable challenge due to their high-dimensional, noisy, and non-Euclidean nature. In this work, we propose a Spatial-Functional Awareness…

Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs…

We propose Continuous Scene Representations (CSR), a scene representation constructed by an embodied agent navigating within a space, where objects and their relationships are modeled by continuous valued embeddings. Our method captures…

Colours are everywhere. They embody a significant part of human visual perception. In this paper, we explore the paradigm of hallucinating colours from a given gray-scale image. The problem of colourization has been dealt in previous…

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning…

Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately,…

The difficulty in obtaining labeled data relevant to a given task is among the most common and well-known practical obstacles to applying deep learning techniques to new or even slightly modified domains. The data volumes required by the…