# Learning Multiple Visual Tasks while Discovering their Structure

Source: [Learning Multiple Visual Tasks while Discovering their Structure](<https://www.sota2.com/research/paper/68fa61d01e209131ce9f6368>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:07:28.348Z

Authors: Carlo Ciliberto, Lorenzo Rosasco, Silvia Villa

Published: 2015-04-13T09:27:23.000Z

## Abstract

Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems, e.g. object detection, classification, tracking of multiple agents, or denoising, to name a few. The key idea is that exploring task relatedness (structure) can lead to improved performances.   In this paper, we propose and study a novel sparse, non-parametric approach exploiting the theory of Reproducing Kernel Hilbert Spaces for vector-valued functions. We develop a suitable regularization framework which can be formulated as a convex optimization problem, and is provably solvable using an alternating minimization approach. Empirical tests show that the proposed method compares favorably to state of the art techniques and further allows to recover interpretable structures, a problem of interest in its own right.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1504.03106>)

[PDF](<https://arxiv.org/pdf/1504.03106.pdf>)
