Dynamic Task Prioritization for Multitask Learning

Guo, Michelle; Haque, Albert; Huang, De-An; Yeung, Serena; Li, Feifei

doi:10.1007/978-3-030-01270-0_17

Cited by 267 publications

(176 citation statements)

References 50 publications

Supporting

Mentioning

176

Contrasting

Order By: Relevance

“…(ii) The ranges of the loss functions from different tasks can be different, which hampers the consistent and balanced optimization of the tasks. (iii) The difficulties of the tasks can be different, which affects the pace with which the tasks are learned, and hence hinders the training process [121]. Figure 14 illustrates a case where the loss of the classification dominates the overall gradient.…”

Section: Imbalance 4: Objective Imbalancementioning

confidence: 99%

“…The hyperparameters in the proposed regularizer control the hardness of not only the instances but also the tasks, and accordingly, the hardness level is increased during training. In another work motivated by the self-paced learning approach, Guo et al [121] use more diverse set of tasks, including object detection. Their method weighs the losses dynamically based on the exponential moving average of a predefined key performance indicator (e.g.…”

Section: Multi-task Learningmentioning

confidence: 99%

See 1 more Smart Citation

Imbalance Problems in Object Detection: A Review

Öksüz

Cam

Kalkan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

412

171

View full text Add to dashboard Cite

In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce two taxonomies; one for the problems and the other for the proposed solutions. Following the taxonomy for the problems, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which categorizes papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: https://github.com/kemaloksuz/ObjectDetectionImbalance.

show abstract

Section: Imbalance 4: Objective Imbalancementioning

confidence: 99%

Section: Multi-task Learningmentioning

confidence: 99%

Imbalance Problems in Object Detection: A Review

Öksüz

Cam

Kalkan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

412

171

View full text Add to dashboard Cite

show abstract

“…(Liu et al, 2018) adds a moving average of task weights obtained by method similar to GradNorm. (Guo et al, 2018) on other hand proposes dynamic weight adjustments based on task difficulty. As the difficulty of learning changes over training time, the task weights are updated allowing the model to prioritize difficult tasks.…”

Section: Multi-task Lossmentioning

confidence: 99%

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

Chennupati

Sistu

Yogamani

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a challenging task which is now becoming mature to be productized in a car. However, semantic annotation is time consuming and quite expensive. Synthetic datasets with domain adaptation techniques have been used to alleviate the lack of large annotated datasets. In this work, we explore an alternate approach of leveraging the annotations of other tasks to improve semantic segmentation. Recently, multi-task learning became a popular paradigm in automated driving which demonstrates joint learning of multiple tasks improves overall performance of each tasks. Motivated by this, we use auxiliary tasks like depth estimation to improve the performance of semantic segmentation task. We propose adaptive task loss weighting techniques to address scale issues in multi-task loss functions which become more crucial in auxiliary tasks. We experimented on automotive datasets including SYNTHIA and KITTI and obtained 3% and 5% improvement in accuracy respectively.1. Construction of auxiliary task learning architecture for semantic segmentation.2. Novel loss function weighting strategy for one main task and one auxiliary task.

show abstract

“…Multi-task Learning: Multi-task learning tries to learn many tasks simultaneously to obtain more general models or multiple outputs in a single run [24,6,14]. Some recent works have addressed the autonomous driving scenario [3,30] so to learn jointly related tasks like depth estimation and semantic segmentation in order to improve performance.…”

Section: Related Workmentioning

confidence: 99%

Learning Across Tasks and Domains

Ramirez

Tonioni

Salti

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Recent works have proven that many relevant visual tasks are closely related one to another. Yet, this connection is seldom deployed in practice due to the lack of practical methodologies to transfer learned concepts across different training processes. In this work, we introduce a novel adaptation framework that can operate across both task and domains. Our framework learns to transfer knowledge across tasks in a fully supervised domain (e.g., synthetic data) and use this knowledge on a different domain where we have only partial supervision (e.g., real data). Our proposal is complementary to existing domain adaptation techniques and extends them to cross tasks scenarios providing additional performance gains. We prove the effectiveness of our framework across two challenging tasks (i.e., monocular depth estimation and semantic segmentation) and four different domains (Synthia, Carla, Kitti, and Cityscapes).

show abstract

Dynamic Task Prioritization for Multitask Learning

Cited by 267 publications

References 50 publications

Imbalance Problems in Object Detection: A Review

Imbalance Problems in Object Detection: A Review

AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving

Learning Across Tasks and Domains

Contact Info

Product

Resources

About