UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks

TL;DR

UniNet is a multi-task scene understanding network that jointly learns object detection, segmentation, and depth estimation, and explores inter-task relationships through adversarial attacks to improve understanding.

Contribution

The paper introduces UniNet, a unified network for multiple scene understanding tasks and analyzes inter-task relationships using adversarial attack techniques.

Findings

Semantic tasks strongly interact with each other.

Geometric tasks also exhibit strong interactions.

Semantic and geometric task relationships are asymmetric and weaken at higher-level features.

Abstract

Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on the other hand, these single tasks are jointly learned, thereby providing an opportunity for tasks to share information and obtain a more comprehensive understanding. To this end, we develop UniNet, a unified scene understanding network that accurately and efficiently infers vital vision tasks including object detection, semantic segmentation, instance segmentation, monocular depth estimation, and monocular instance depth prediction. As these tasks look at different semantic and geometric information, they can either complement or conflict with each other. Therefore, understanding inter-task relationships can provide useful cues to enable complementary information sharing. We evaluate the task relationships in UniNet through the lens of adversarial attacks based on the notion that they can exploit learned biases and task interactions in the neural network. Extensive experiments on the Cityscapes dataset, using untargeted and targeted attacks reveal that semantic tasks strongly interact amongst themselves, and the same holds for geometric tasks. Additionally, we show that the relationship between semantic and geometric tasks is asymmetric and their interaction becomes weaker as we move towards higher-level representations.