Skip to search formSkip to main contentSkip to account menu

Context Encoders: Feature Learning by Inpainting

It is found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures, and can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.
View on IEEE (opens in a new tab)

Curiosity-Driven Exploration by Self-Supervised Prediction

This work forms curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model, which scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and ignores the aspects of the environment that cannot affect the agent.
View on IEEE (opens in a new tab)

Toward Multimodal Image-to-Image Translation

This work aims to model a distribution of possible outputs in a conditional generative modeling setting that helps prevent a many-to-one mapping from the latent code to the output during training, also known as the problem of mode collapse.
View PDF on arXiv (opens in a new tab)

Large-Scale Study of Curiosity-Driven Learning

This paper performs the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite, and shows surprisingly good performance.
View PDF on arXiv (opens in a new tab)

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

This work proposes Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space of a CNN, and demonstrates the generality of this new learning framework.
View on IEEE (opens in a new tab)

Self-Supervised Exploration via Disagreement

This paper proposes a formulation for exploration inspired by the work in active learning literature and trains an ensemble of dynamics models and incentivizes the agent to explore such that the disagreement of those ensembles is maximized, which results in a sample-efficient exploration.
View PDF on arXiv (opens in a new tab)

Learning Features by Watching Objects Move

Inspired by the human visual system, low-level motion-based grouping cues can be used to learn an effective visual representation that significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target task is scarce.
View on IEEE (opens in a new tab)

Fully Convolutional Multi-Class Multiple Instance Learning

This work proposes a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network that exploits the further supervision given by images with multiple labels.
View PDF on arXiv (opens in a new tab)

Zero-Shot Visual Imitation

This workmitating expert demonstration is a powerful mechanism for learning to perform tasks from raw sensory observations by providing multiple demonstrations of a task at training time, and this generates data in the form of observation-action pairs from the agent's point of view.
View on IEEE (opens in a new tab)

Planning to Explore via Self-Supervised World Models

Without any training supervision or task-specific interaction, Plan2Explore outperforms prior self-supervised exploration methods, and in fact, almost matches the performances oracle which has access to rewards.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)