Incorporating simulated spatial context information improves the effectiveness of contrastive learning models
- URL: http://arxiv.org/abs/2401.15120v2
- Date: Wed, 27 Mar 2024 15:49:52 GMT
- Title: Incorporating simulated spatial context information improves the effectiveness of contrastive learning models
- Authors: Lizhen Zhu, James Z. Wang, Wonseuk Lee, Brad Wyble,
- Abstract summary: We present a unique approach, termed Environmental Spatial Similarity (ESS), that complements existing contrastive learning methods.
ESS allows remarkable proficiency in room classification and spatial prediction tasks, especially in unfamiliar environments.
Potentially transformative applications span from robotics to space exploration.
- Score: 1.4179832037924995
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visual learning often occurs in a specific context, where an agent acquires skills through exploration and tracking of its location in a consistent environment. The historical spatial context of the agent provides a similarity signal for self-supervised contrastive learning. We present a unique approach, termed Environmental Spatial Similarity (ESS), that complements existing contrastive learning methods. Using images from simulated, photorealistic environments as an experimental setting, we demonstrate that ESS outperforms traditional instance discrimination approaches. Moreover, sampling additional data from the same environment substantially improves accuracy and provides new augmentations. ESS allows remarkable proficiency in room classification and spatial prediction tasks, especially in unfamiliar environments. This learning paradigm has the potential to enable rapid visual learning in agents operating in new environments with unique visual characteristics. Potentially transformative applications span from robotics to space exploration. Our proof of concept demonstrates improved efficiency over methods that rely on extensive, disconnected datasets.
Related papers
- Robust Visual Imitation Learning with Inverse Dynamics Representations [32.806294517277976]
We develop an inverse dynamics state representation learning objective to align the expert environment and the learning environment.
With the abstract state representation, we design an effective reward function, which thoroughly measures the similarity between behavior data and expert data.
Our approach can achieve a near-expert performance in most environments, and significantly outperforms the state-of-the-art visual IL methods and robust IL methods.
arXiv Detail & Related papers (2023-10-22T11:47:35Z) - Improving Reinforcement Learning Efficiency with Auxiliary Tasks in
Non-Visual Environments: A Comparison [0.0]
This study compares common auxiliary tasks based on, to the best of our knowledge, the only decoupled representation learning method for low-dimensional non-visual observations.
Our findings show that representation learning with auxiliary tasks only provides performance gains in sufficiently complex environments.
arXiv Detail & Related papers (2023-10-06T13:22:26Z) - Hyperbolic Contrastive Learning [12.170564544949308]
We propose a novel contrastive learning framework to learn semantic relationships in the hyperbolic space.
We show that our proposed method achieves better results on self-supervised pretraining, supervised classification, and higher robust accuracy than baseline methods.
arXiv Detail & Related papers (2023-02-02T20:47:45Z) - Stochastic Coherence Over Attention Trajectory For Continuous Learning
In Video Streams [64.82800502603138]
This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream.
The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations.
Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
arXiv Detail & Related papers (2022-04-26T09:52:31Z) - Visual Adversarial Imitation Learning using Variational Models [60.69745540036375]
Reward function specification remains a major impediment for learning behaviors through deep reinforcement learning.
Visual demonstrations of desired behaviors often presents an easier and more natural way to teach agents.
We develop a variational model-based adversarial imitation learning algorithm.
arXiv Detail & Related papers (2021-07-16T00:15:18Z) - Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration
Under Uncertainty [6.42522897323111]
We present a framework for self-learning a high-performance exploration policy in a single simulation environment.
We propose a novel approach that uses graph neural networks in conjunction with deep reinforcement learning.
arXiv Detail & Related papers (2021-05-11T02:42:17Z) - Geography-Aware Self-Supervised Learning [79.4009241781968]
We show that due to their different characteristics, a non-trivial gap persists between contrastive and supervised learning on standard benchmarks.
We propose novel training methods that exploit the spatially aligned structure of remote sensing data.
Our experiments show that our proposed method closes the gap between contrastive and supervised learning on image classification, object detection and semantic segmentation for remote sensing.
arXiv Detail & Related papers (2020-11-19T17:29:13Z) - Heterogeneous Contrastive Learning: Encoding Spatial Information for
Compact Visual Representations [183.03278932562438]
This paper presents an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations.
We show that our approach achieves higher efficiency in visual representations and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
arXiv Detail & Related papers (2020-11-19T16:26:25Z) - Evidential Sparsification of Multimodal Latent Spaces in Conditional
Variational Autoencoders [63.46738617561255]
We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder.
We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not.
Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
arXiv Detail & Related papers (2020-10-19T01:27:21Z) - Learning Invariant Representations for Reinforcement Learning without
Reconstruction [98.33235415273562]
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction.
Bisimulation metrics quantify behavioral similarity between states in continuous MDPs.
We demonstrate the effectiveness of our method at disregarding task-irrelevant information using modified visual MuJoCo tasks.
arXiv Detail & Related papers (2020-06-18T17:59:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.