SLYKLatent, a Learning Framework for Facial Features Estimation
- URL: http://arxiv.org/abs/2402.01555v1
- Date: Fri, 2 Feb 2024 16:47:18 GMT
- Title: SLYKLatent, a Learning Framework for Facial Features Estimation
- Authors: Samuel Adebayo, Joost C. Dessing, Se\'an McLoone
- Abstract summary: SLYKLatent is a novel approach for enhancing gaze estimation by addressing appearance instability challenges in datasets.
Our evaluation on benchmark datasets achieves an 8.7% improvement on Gaze360, rivals top MPIIFaceGaze results, and leads on a subset of ETH-XGaze by 13%.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this research, we present SLYKLatent, a novel approach for enhancing gaze
estimation by addressing appearance instability challenges in datasets due to
aleatoric uncertainties, covariant shifts, and test domain generalization.
SLYKLatent utilizes Self-Supervised Learning for initial training with facial
expression datasets, followed by refinement with a patch-based tri-branch
network and an inverse explained variance-weighted training loss function. Our
evaluation on benchmark datasets achieves an 8.7% improvement on Gaze360,
rivals top MPIIFaceGaze results, and leads on a subset of ETH-XGaze by 13%,
surpassing existing methods by significant margins. Adaptability tests on
RAF-DB and Affectnet show 86.4% and 60.9% accuracies, respectively. Ablation
studies confirm the effectiveness of SLYKLatent's novel components. This
approach has strong potential in human-robot interaction.
Related papers
- Multiple Instance Learning with random sampling for Whole Slide Image
Classification [0.0]
Random sampling of patches during training is computationally efficient and serves as a regularization strategy.
We find optimal performance enhancement of 1.7% using thirty percent of patches on the CAMELYON16 dataset, and 3.7% with only eight samples on the TUPAC16 dataset.
We also find interpretability effects are strongly dataset-dependent, with interpretability impacted on CAMELYON16, while remaining unaffected on TUPAC16.
arXiv Detail & Related papers (2024-03-08T14:31:40Z) - The Risk of Federated Learning to Skew Fine-Tuning Features and
Underperform Out-of-Distribution Robustness [50.52507648690234]
Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model.
We introduce three robustness indicators and conduct experiments across diverse robust datasets.
Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
arXiv Detail & Related papers (2024-01-25T09:18:51Z) - SSL-CPCD: Self-supervised learning with composite pretext-class
discrimination for improved generalisability in endoscopic image analysis [3.1542695050861544]
Deep learning-based supervised methods are widely popular in medical image analysis.
They require a large amount of training data and face issues in generalisability to unseen datasets.
We propose to explore patch-level instance-group discrimination and penalisation of inter-class variation using additive angular margin.
arXiv Detail & Related papers (2023-05-31T21:28:08Z) - Learning Diversified Feature Representations for Facial Expression
Recognition in the Wild [97.14064057840089]
We propose a mechanism to diversify the features extracted by CNN layers of state-of-the-art facial expression recognition architectures.
Experimental results on three well-known facial expression recognition in-the-wild datasets, AffectNet, FER+, and RAF-DB, show the effectiveness of our method.
arXiv Detail & Related papers (2022-10-17T19:25:28Z) - Training Strategies for Improved Lip-reading [61.661446956793604]
We investigate the performance of state-of-the-art data augmentation approaches, temporal models and other training strategies.
A combination of all the methods results in a classification accuracy of 93.4%, which is an absolute improvement of 4.6% over the current state-of-the-art performance.
An error analysis of the various training strategies reveals that the performance improves by increasing the classification accuracy of hard-to-recognise words.
arXiv Detail & Related papers (2022-09-03T09:38:11Z) - ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through
Regularized Self-Attention [48.697458429460184]
Two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer.
This paper proposes a well-designed model named ERNIE-Sparse.
It consists of two distinctive parts: (i) Hierarchical Sparse Transformer (HST) to sequentially unify local and global information, and (ii) Self-Attention Regularization (SAR) to minimize the distance for transformers with different attention topologies.
arXiv Detail & Related papers (2022-03-23T08:47:01Z) - A new weakly supervised approach for ALS point cloud semantic
segmentation [1.4620086904601473]
We propose a deep-learning based weakly supervised framework for semantic segmentation of ALS point clouds.
We exploit potential information from unlabeled data subject to incomplete and sparse labels.
Our method achieves an overall accuracy of 83.0% and an average F1 score of 70.0%, which have increased by 6.9% and 12.8% respectively.
arXiv Detail & Related papers (2021-10-04T14:00:23Z) - Consistency and Monotonicity Regularization for Neural Knowledge Tracing [50.92661409499299]
Knowledge Tracing (KT) tracking a human's knowledge acquisition is a central component in online learning and AI in Education.
We propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses.
Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances.
arXiv Detail & Related papers (2021-05-03T02:36:29Z) - Generic Semi-Supervised Adversarial Subject Translation for Sensor-Based
Human Activity Recognition [6.2997667081978825]
This paper presents a novel generic and robust approach for semi-supervised domain adaptation in Human Activity Recognition.
It capitalizes on the advantages of the adversarial framework to tackle the shortcomings, by leveraging knowledge from annotated samples exclusively from the source subject and unlabeled ones of the target subject.
The results demonstrate the effectiveness of our proposed algorithms over state-of-the-art methods, which led in up to 13%, 4%, and 13% improvement of our high-level activities recognition metrics for Opportunity, LISSI, and PAMAP2 datasets.
arXiv Detail & Related papers (2020-11-11T12:16:23Z) - Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner
Party Transcription [73.66530509749305]
In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline.
We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures.
Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
arXiv Detail & Related papers (2020-04-22T19:08:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.