Corpus ID: 218665674

Taskology: Utilizing Task Relations at Scale

@inproceedings{Lu2021TaskologyUT,
  title={Taskology: Utilizing Task Relations at Scale},
  author={Yao Lu and S{\"o}ren Pirk and Jan Dlabal and Anthony Brohan and Ankita Pasad and Zhao Chen and Vincent Casser and Anelia Angelova and A. Gordon},
  booktitle={CVPR},
  year={2021}
}
It has been recognized that the joint training of computer vision tasks with shared network components enables higher performance for each individual task. Training tasks together allows learning the inherent relationships among them; however, this requires large sets of labeled data. Instead, we argue that utilizing the known relationships between tasks explicitly allows improving their performance with less labeled data. To this end, we aim to establish and explore a novel approach for the… Expand

Figures and Tables from this paper

Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
TLDR
It is shown how prediction of different representations such as depth, semantic segmentation, surface normals and pose from RGB input could be effectively learned through self-supervised consensus in a graph of neural networks. Expand
Single Image Depth Estimation: An Overview
TLDR
This work reviews solutions to the problem of depth estimation, arguably the most important subtask in scene understanding, and examines non-deep learning approaches that mostly predate deep learning and utilize hand-crafted features and assumptions, and more recent works that mostly use deep learning techniques. Expand
CARLS: Cross-platform Asynchronous Representation Learning System
TLDR
The proposed CARLS is particularly suitable for learning paradigms where model training benefits from additional knowledge inferred or discovered during training, such as node embeddings for graph neural networks or reliable pseudo labels from model predictions. Expand

References

SHOWING 1-10 OF 100 REFERENCES
Taskonomy: Disentangling Task Transfer Learning
TLDR
This work proposes a fully computational approach for modeling the structure of space of visual tasks via finding (first and higher-order) transfer learning dependencies across a dictionary of twenty six 2D, 2.5D, 3D, and semantic tasks in a latent space and provides a computational taxonomic map for task transfer learning. Expand
Multi-task Self-Supervised Visual Learning
TLDR
The results show that deeper networks work better, and that combining tasks—even via a na¨ýve multihead architecture—always improves performance. Expand
Integrated perception with recurrent multi-task neural networks
TLDR
This work proposes a new architecture, which it calls "MultiNet", in which not only deep image features are shared between tasks, but where tasks can interact in a recurrent manner by encoding the results of their analysis in a common shared representation of the data. Expand
Multi-task Learning with Labeled and Unlabeled Tasks
TLDR
Focusing on an instance-based transfer method, this work derives an algorithm for making the choice of labeled tasks and for transferring information between the tasks in a principled way and illustrates the effectiveness of the algorithm by experiments on synthetic and real data. Expand
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
TLDR
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. Expand
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory
  • I. Kokkinos
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
In this work we train in an end-to-end manner a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a network can act likeExpand
Representation Learning by Learning to Count
TLDR
This paper uses two image transformations in the context of counting: scaling and tiling to train a neural network with a contrastive loss that produces representations that perform on par or exceed the state of the art in transfer learning benchmarks. Expand
Transitive Invariance for Self-Supervised Visual Representation Learning
TLDR
This paper proposes to generate a graph with millions of objects mined from hundreds of thousands of videos and argues to organize and reason the data with multiple variations to exploit different self-supervised approaches to learn representations invariant to inter-instance variations. Expand
Unsupervised Visual Representation Learning by Context Prediction
TLDR
It is demonstrated that the feature representation learned using this within-image context indeed captures visual similarity across images and allows us to perform unsupervised visual discovery of objects like cats, people, and even birds from the Pascal VOC 2011 detection dataset. Expand
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
TLDR
A novel unsupervised learning approach to build features suitable for object detection and classification and to facilitate the transfer of features to other tasks, the context-free network (CFN), a siamese-ennead convolutional neural network is introduced. Expand
...
1
2
3
4
5
...