Related papers: A General Purpose Supervisory Signal for Embodied …

Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under…

Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to…

Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation and memory costs. Thus, it remains a great challenge to…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

We study self-supervised learning on graphs using contrastive methods. A general scheme of prior methods is to optimize two-view representations of input graphs. In many studies, a single graph-level representation is computed as one of the…

Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning…

Goal-oriented semantic communication (SC) aims to revolutionize communication systems by transmitting only task-essential information. However, current approaches face challenges such as joint training at transceivers, leading to redundant…

We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment. Given an embodied agent trained in a noiseless environment, our objective is to transfer the agent to a noisy…

Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs,…

Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to geo-located datasets, e.g. remote sensing, where…

In this work, we consider one-shot imitation learning for object rearrangement tasks, where an AI agent needs to watch a single expert demonstration and learn to perform the same task in different environments. To achieve a strong…

We propose a new method for improving zero-shot ObjectNav that aims to utilize potentially available environmental percepts for navigational assistance. Our approach takes into account that the ground agent may have limited and sometimes…

Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…

This paper presents a new adversarial training framework for image inpainting with segmentation confusion adversarial training (SCAT) and contrastive learning. SCAT plays an adversarial game between an inpainting generator and a…

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous…

SCONE-GAN presents an end-to-end image translation, which is shown to be effective for learning to generate realistic and diverse scenery images. Most current image-to-image translation approaches are devised as two mappings: a translation…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…