Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection

Abstract : Multi-Task Learning (MTL) is appealing for deep learning regularization. In this paper, we tackle a specific MTL context denoted as primary MTL, where the ultimate goal is to improve the performance of a given primary task by leveraging several other auxiliary tasks. Our main methodological contribution is to introduce ROCK, a new generic multi-modal fusion block for deep learning tailored to the primary MTL context. ROCK architecture is based on a residual connection, which makes forward prediction explicitly impacted by the intermediate auxiliary representations. The auxiliary predictor's architecture is also specifically designed to our primary MTL context, by incorporating intensive pooling operators for maximizing complementarity of intermediate representations. Extensive experiments on NYUv2 dataset (object detection with scene classification, depth prediction, and surface normal estimation as auxiliary tasks) validate the relevance of the approach and its superiority to flat MTL approaches. Our method outperforms state-of-the-art object detection models on NYUv2 by a large margin, and is also able to handle large-scale heterogeneous inputs (real and synthetic images) with missing annotation modalities.
Complete list of metadatas

Cited literature [51 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-01922291
Contributor : Taylor Mordan <>
Submitted on : Thursday, December 20, 2018 - 12:24:27 PM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM
Long-term archiving on : Friday, March 22, 2019 - 12:22:25 PM

File

ROCK.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01922291, version 3

Citation

Taylor Mordan, Nicolas Thome, Gilles Henaff, Matthieu Cord. Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection. 32nd Conference on Neural Information Processing Systems (NeurIPS), Dec 2018, Montréal, Canada. ⟨hal-01922291v3⟩

Share

Metrics

Record views

124

Files downloads

36