Learning Perceptual Inference by Contrasting

by   Chi Zhang, et al.

"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology development. Modern Artificial Intelligence (AI), fueled by massive datasets, deeper models, and mighty computation, has come to a stage where (super-)human-level performances are observed in certain specific tasks. However, current AI's ability in "thinking in pictures" is still far lacking behind. In this work, we study how to improve machines' reasoning ability on one challenging task of this kind: Raven's Progressive Matrices (RPM). Specifically, we borrow the very idea of "contrast effects" from the field of psychology, cognition, and education to design and train a permutation-invariant model. Inspired by cognitive studies, we equip our model with a simple inference module that is jointly trained with the perception backbone. Combining all the elements, we propose the Contrastive Perceptual Inference network (CoPINet) and empirically demonstrate that CoPINet sets the new state-of-the-art for permutation-invariant models on two major datasets. We conclude that spatial-temporal reasoning depends on envisaging the possibilities consistent with the relations between objects and can be solved from pixel-level inputs.


page 1

page 2

page 3

page 4


Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

Spatial-temporal reasoning is a challenging task in Artificial Intellige...

Cognitive Interpretation of Everyday Activities: Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation

We position a narrative-centred computational model for high-level knowl...

Neuro-Symbolic Spatio-Temporal Reasoning

Knowledge about space and time is necessary to solve problems in the phy...

Hybrid Intelligence

Research has a long history of discussing what is superior in predicting...

Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence

The problem of replicating the flexibility of human common-sense reasoni...

Bayesian inference of spatial and temporal relations in AI patents for EU countries

In the paper, we propose two models of Artificial Intelligence (AI) pate...

Please sign up or login with your details

Forgot password? Click here to reset