• Corpus ID: 233423345

Exploring Relational Context for Multi-Task Dense Prediction

  title={Exploring Relational Context for Multi-Task Dense Prediction},
  author={David Bruggemann and Menelaos Kanakis and Anton Obukhov and Stamatios Georgoulis and Luc Van Gool},
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a multi-task environment for dense prediction tasks, represented by a common backbone and independent task-specific heads. Our goal is to find the most efficient way to refine each task prediction by capturing cross-task contexts dependent on tasks’ relations… 
Learning Multiple Dense Prediction Tasks from Partially Annotated Data
This paper proposes a multi-task training procedure that successfully leverages task relations to supervise its multi- task learning when data is partially annotated, and learns to map each task pair to a joint pairwise task-space which enables sharing information between them in a computationally efficient way through another network conditioned on task pairs.
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
PolyphonicFormer, a vision transformer to unify all the subtasks under the DVPS task, is presented, which explores the relationship between depth estimation and panoptic segmentation via query-based learning and proposes to learn the correlations among these queries via gated fusion.
Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder
This work classifies sewer pipe defects and properties concurrently and presents a novel decoder-focused multi-task classification architecture Cross-Task Graph Neural Network (CT-GNN), which refines the disjointed per-task predictions using cross-task information.
Efficient Visual Tracking with Exemplar Transformers
This paper introduces the Exemplar Transformer, an efficient transformer for real-time visual object tracking that consistently outperforms all other methods on the LaSOT, OTB-100, NFS, TrackingNet, and VOT-ST2020 datasets.


End-To-End Multi-Task Learning With Attention
The proposed Multi-Task Attention Network (MTAN) consists of a single shared network containing a global feature pool, together with a soft-attention module for each task, which allows learning of task-specific feature-level attention.
Branched Multi-Task Networks: Deciding what layers to share
This paper proposes an approach to automatically construct branched multi-task networks, by leveraging the employed tasks' affinities, given a specific budget, and generates architectures, in which shallow layers are task-agnostic, whereas deeper ones gradually grow more task-specific.
MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning
A novel single-shot gradient-based search algorithm that closes the performance gap between the searched architectures and the final evaluation architecture and achieves a single model, which can be directly used for evaluation without (re-)training from scratch.
PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
This paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate Auxiliary tasks are utilized as multi-modal input via the authors' proposed multi- modal distillation modules for the final tasks.
Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
Evaluation on person attributes classification tasks involving facial and clothing attributes suggests that the models produced by the proposed method are fast, compact and can closely match or exceed the state-of-the-art accuracy from strong baselines by much more expensive models.
Automated Search for Resource-Efficient Branched Multi-Task Networks
A principled approach, rooted in differentiable neural architecture search, to automatically define branching (tree-like) structures in the encoding stage of a multi-task neural network to allow flexibility within resource-constrained environments is proposed.
Attentive Single-Tasking of Multiple Tasks
In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as
Dual Attention Network for Scene Segmentation
New state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset is achieved without using coarse data.
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
A principled approach to multi-task deep learning is proposed which weighs multiple loss functions by considering the homoscedastic uncertainty of each task, allowing us to simultaneously learn various quantities with different units or scales in both classification and regression settings.
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
The reparameterization enables the model to learn new tasks without adversely affecting the performance of existing ones and achieves state-of-the-art on two challenging multi-task learning benchmarks, PASCAL-Context and NYUD, and also demonstrates superior incremental learning capability as compared to its close competitors.