paper-with-me

Papers

Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation

2021-05-13 · Mahdi Pourmirzaei, Gholam Ali Montazer, Farzaneh Esmaili

In this paper, at first, the impact of ImageNet pre-training on fine-grained Facial Emotion Recognition (FER) is investigated which shows that when enough augmentations on images are applied, training from scratch provides better result than fine-tuning on ImageNet pre-training. Next, we propose a method to improve fine-grained and in-the-wild FER, called Hybrid Multi-Task Learning (HMTL). HMTL uses Self-Supervised Learning (SSL) as an auxiliary task during classical Supervised Learning (SL) in the form of Multi-Task Learning (MTL). Leveraging SSL during training can gain additional information from images for the primary fine-grained SL task. We investigate how proposed HMTL can be used in the FER domain by designing two customized version of common pre-text task techniques, puzzling and in-painting. We achieve state-of-the-art results on the AffectNet benchmark via two types of HMTL, without utilizing pre-training on additional data. Experimental results on the common SSL pre-training and proposed HMTL demonstrate the difference and superiority of our work. However, HMTL is not only limited to FER domain. Experiments on two types of fine-grained facial tasks, i.e., head pose estimation and gender recognition, reveals the potential of using HMTL to improve fine-grained facial representation.

📄 PDF Abstract BibTeX arXiv:2105.06421

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion RecognitionFacial Emotion RecognitionFacial Expression Recognition (FER)Head Pose EstimationMulti-Task LearningPose EstimationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
Sigmoid Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Adabelief 설명 없음
Squeeze-and-Excitation Block The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature…

Similar Papers 제목 키워드 기반

Adaptive Transfer Learning on Graph Neural Networks

2021-07-19 · Xueting Han, Zhenhuan Huang, Bang An, Jing Bai

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further i…

Meta-LearningMulti-Task LearningTransfer Learning

Automatic Self-supervised Learning for Social Recommendations

2024-12-25 · Xin He, Wenqi Fan, Mingchen Sun, Ying Wang 외

In recent years, researchers have attempted to exploit social relations to improve the performance in recommendation systems. Generally, most existing social recommendation methods heavily depends on substantial domain k…

Meta-LearningRecommendation SystemsRepresentation LearningSelf-Supervised Learning

Intrinsically Motivated Self-supervised Learning in Reinforcement Learning

2021-06-26 · Yue Zhao, Chenzhuang Du, Hang Zhao, Tiejun Li

In vision-based reinforcement learning (RL) tasks, it is prevalent to assign auxiliary tasks with a surrogate self-supervised loss so as to obtain more semantic representations and improve sample efficiency. However, abu…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

2021-03-01 · Dasol Hwang, Jinyoung Park, Sunyoung Kwon, Kyung-Min Kim 외

In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various applications such as link prediction, no…

Auxiliary LearningGraph Neural NetworkLink PredictionMeta-Learning+3

Self-Supervised Generalisation with Meta Auxiliary Learning

2019-01-25 · NeurIPS 2019 12 · Shikun Liu, Andrew J. Davison, Edward Johns

Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate …

Auxiliary LearningMeta-LearningMulti-Task Learning