Deep Joint Task Learning for Generic Object Extraction

TL;DR

This paper introduces a joint deep learning framework that simultaneously localizes and segments objects in images, significantly improving accuracy and speed over previous methods by integrating two CNNs with latent variables and an EM optimization process.

Contribution

It presents a novel joint task learning approach combining object localization and segmentation CNNs with latent variables and EM optimization, enhancing performance without hand-crafted features.

Findings

Outperforms state-of-the-art methods in accuracy

Achieves 1000 times faster processing speed

Effectively integrates localization and segmentation tasks

Abstract

This paper investigates how to extract objects-of-interest without relying on hand-craft features and sliding windows approaches, that aims to jointly solve two sub-tasks: (i) rapidly localizing salient objects from images, and (ii) accurately segmenting the objects based on the localizations. We present a general joint task learning framework, in which each task (either object localization or object segmentation) is tackled via a multi-layer convolutional neural network, and the two networks work collaboratively to boost performance. In particular, we propose to incorporate latent variables bridging the two networks in a joint optimization manner. The first network directly predicts the positions and scales of salient objects from raw images, and the latent variables adjust the object localizations to feed the second network that produces pixelwise object masks. An EM-type method is presented for the optimization, iterating with two steps: (i) by using the two networks, it estimates the latent variables by employing an MCMC-based sampling method; (ii) it optimizes the parameters of the two networks unitedly via back propagation, with the fixed latent variables. Extensive experiments suggest that our framework significantly outperforms other state-of-the-art approaches in both accuracy and efficiency (e.g. 1000 times faster than competing approaches).