Learning to see like children: proof of concept

TL;DR

This paper introduces a developmental learning framework for visual agents that mimics children's learning, leveraging motion coherence and minimal supervision to achieve semantic labeling in complex environments.

Contribution

It proposes a novel protocol for visual learning inspired by children, utilizing motion coherence and constraints, with a lifelong learning approach and crowd-sourced evaluation.

Findings

Semantic labeling emerges with few supervised examples.

Motion coherence provides extensive supervision signals.

Framework supports lifelong learning without clear training/test separation.

Abstract

In the last few years we have seen a growing interest in machine learning approaches to computer vision and, especially, to semantic labeling. Nowadays state of the art systems use deep learning on millions of labeled images with very successful results on benchmarks, though it is unlikely to expect similar results in unrestricted visual environments. Most learning schemes essentially ignore the inherent sequential structure of videos: this might be a critical issue, since any visual recognition process is remarkably more complex when shuffling video frames. Based on this remark, we propose a re-foundation of the communication protocol between visual agents and the environment, which is referred to as learning to see like children. Like for human interaction, visual concepts are acquired by the agents solely by processing their own visual stream along with human supervisions on selected pixels. We give a proof of concept that remarkable semantic labeling can emerge within this protocol by using only a few supervised examples. This is made possible by exploiting a constraint of motion coherent labeling that virtually offers tons of supervisions. Additional visual constraints, including those associated with object supervisions, are used within the context of learning from constraints. The framework is extended in the direction of lifelong learning, so as our visual agents live in their own visual environment without distinguishing learning and test set. Learning takes place in deep architectures under a progressive developmental scheme. In order to evaluate our Developmental Visual Agents (DVAs), in addition to classic benchmarks, we open the doors of our lab, allowing people to evaluate DVAs by crowd-sourcing. Such assessment mechanism might result in a paradigm shift in methodologies and algorithms for computer vision, encouraging truly novel solutions within the proposed framework.