paper-with-me

홈 › Papers

Learning Multiple Pixelwise Tasks Based on Loss Scale Balancing

2021-01-01 · ICCV 2021 10 · Jae-Han Lee, Chul Lee, Chang-Su Kim

We propose a novel loss weighting algorithm, called loss scale balancing (LSB), for multi-task learning (MTL) of pixelwise vision tasks. An MTL model is trained to estimate multiple pixelwise predictions using an overall loss, which is a linear combination of individual task losses. The proposed algorithm dynamically adjusts the linear weights to learn all tasks effectively. Instead of controlling the trend of each loss value directly, we balance the loss scale --- the product of the loss value and its weight --- periodically. In addition, by evaluating the difficulty of each task based on the previous loss record, the proposed algorithm focuses more on difficult tasks during training. Experimental results show that the proposed algorithm outperforms conventional weighting algorithms for MTL of various pixelwise tasks. Codes are available at https://github.com/jaehanlee-mcl/LSB-MTL.

📄 PDF Abstract BibTeX

Code (1)

jaehanlee-mcl/lsb-mtl 공식 구현

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Dual-Balancing for Multi-Task Learning

2023-08-23 · Baijiong Lin, Weisen Jiang, Feiyang Ye, Yu Zhang 외

Multi-task learning (MTL), a learning paradigm to learn multiple related tasks simultaneously, has achieved great success in various fields. However, task balancing problem remains a significant challenge in MTL, with th…

Multi-Task Learning

Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?

2022-03-21 · Ryan Lagerquist, Imme Ebert-Uphoff

In the last decade, much work in atmospheric science has focused on spatial verification (SV) methods for gridded prediction, which overcome serious disadvantages of pixelwise verification. However, neural networks (NN) …

Multi-label Pixelwise Classification for Reconstruction of Large-scale Urban Areas

2017-09-21 · Yuanlie He, Sudhir Mudur, Charalambos Poullis

Object classification is one of the many holy grails in computer vision and as such has resulted in a very large number of algorithms being proposed already. Specifically in recent years there has been considerable progr…

ClassificationGeneral ClassificationObject

Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies

2022-11-22 · Anish Lakkapragada, Essam Sleiman, Saimourya Surabhi, Dennis P. Wall

Multi-Task Learning (MTL) is a growing subject of interest in deep learning, due to its ability to train models more efficiently on multiple tasks compared to using a group of conventional single-task models. However, MT…

Multi-Task Learning

Fully Convolutional Multi-Class Multiple Instance Learning

2014-12-22 · Deepak Pathak, Evan Shelhamer, Jonathan Long, Trevor Darrell

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semanti…

Multiple Instance LearningSegmentationSemantic SegmentationWeakly-Supervised Semantic Segmentation