Intrinsic Physical Concepts Discovery with Object-Centric Predictive
Models
- URL: http://arxiv.org/abs/2303.01869v3
- Date: Sun, 9 Apr 2023 12:56:44 GMT
- Title: Intrinsic Physical Concepts Discovery with Object-Centric Predictive
Models
- Authors: Qu Tang, XiangYu Zhu, Zhen Lei, ZhaoXiang Zhang
- Abstract summary: We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision.
We show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks.
- Score: 86.25460882547581
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The ability to discover abstract physical concepts and understand how they
work in the world through observing lies at the core of human intelligence. The
acquisition of this ability is based on compositionally perceiving the
environment in terms of objects and relations in an unsupervised manner. Recent
approaches learn object-centric representations and capture visually observable
concepts of objects, e.g., shape, size, and location. In this paper, we take a
step forward and try to discover and represent intrinsic physical concepts such
as mass and charge. We introduce the PHYsical Concepts Inference NEtwork
(PHYCINE), a system that infers physical concepts in different abstract levels
without supervision. The key insights underlining PHYCINE are two-fold,
commonsense knowledge emerges with prediction, and physical concepts of
different abstract levels should be reasoned in a bottom-up fashion. Empirical
evaluation demonstrates that variables inferred by our system work in
accordance with the properties of the corresponding physical concepts. We also
show that object representations containing the discovered physical concepts
variables could help achieve better performance in causal reasoning tasks,
i.e., ComPhy.
Related papers
- Compositional Physical Reasoning of Objects and Events from Videos [122.6862357340911]
This paper addresses the challenge of inferring hidden physical properties from objects' motion and interactions.
We evaluate state-of-the-art video reasoning models on ComPhy and reveal their limited ability to capture these hidden properties.
We also propose a novel neuro-symbolic framework, Physical Concept Reasoner (PCR), that learns and reasons about both visible and hidden physical properties.
arXiv Detail & Related papers (2024-08-02T15:19:55Z) - Physical Property Understanding from Language-Embedded Feature Fields [27.151380830258603]
We present a novel approach for dense prediction of the physical properties of objects using a collection of images.
Inspired by how humans reason about physics through vision, we leverage large language models to propose candidate materials for each object.
Our method is accurate, annotation-free, and applicable to any object in the open world.
arXiv Detail & Related papers (2024-04-05T17:45:07Z) - ContPhy: Continuum Physical Concept Learning and Reasoning from Videos [86.63174804149216]
ContPhy is a novel benchmark for assessing machine physical commonsense.
We evaluated a range of AI models and found that they still struggle to achieve satisfactory performance on ContPhy.
We also introduce an oracle model (ContPRO) that marries the particle-based physical dynamic models with the recent large language models.
arXiv Detail & Related papers (2024-02-09T01:09:21Z) - On Binding Objects to Symbols: Learning Physical Concepts to Understand
Real from Fake [155.6741526791004]
We revisit the classic signal-to-symbol barrier in light of the remarkable ability of deep neural networks to generate synthetic data.
We characterize physical objects as abstract concepts and use the previous analysis to show that physical objects can be encoded by finite architectures.
We conclude that binding physical entities to digital identities is possible in finite time with finite resources.
arXiv Detail & Related papers (2022-07-25T17:21:59Z) - ComPhy: Compositional Physical Reasoning of Objects and Events from
Videos [113.2646904729092]
The compositionality between the visible and hidden properties poses unique challenges for AI models to reason from the physical world.
Existing studies on video reasoning mainly focus on visually observable elements such as object appearance, movement, and contact interaction.
We propose an oracle neural-symbolic framework named Compositional Physics Learner (CPL), combining visual perception, physical property learning, dynamic prediction, and symbolic execution.
arXiv Detail & Related papers (2022-05-02T17:59:13Z) - Curiosity-driven Intuitive Physics Learning [0.0]
We propose a model for curiosity-driven learning and inference for real-world AI agents.
This model is based on the arousal of curiosity, deriving from observations along discontinuities in the fundamental macroscopic solid-body physics parameters.
The model aims to support the emulation of learning from scratch followed by substantiation through experience, irrespective of domain.
arXiv Detail & Related papers (2021-05-16T12:58:05Z) - Visual Grounding of Learned Physical Models [66.04898704928517]
Humans intuitively recognize objects' physical properties and predict their motion, even when the objects are engaged in complicated interactions.
We present a neural model that simultaneously reasons about physics and makes future predictions based on visual and dynamics priors.
Experiments show that our model can infer the physical properties within a few observations, which allows the model to quickly adapt to unseen scenarios and make accurate predictions into the future.
arXiv Detail & Related papers (2020-04-28T17:06:38Z)
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.