HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images

• URL: http://arxiv.org/abs/2207.09508v2
• Date: Thu, 21 Jul 2022 14:20:55 GMT
• Title: HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images
• Authors: Andrey V. Savchenko
• Abstract summary: We present the results of the HSE-NN team in the 4th competition on Affective Behavior Analysis in-the-wild (ABAW) The novel multi-task EfficientNet model is trained for simultaneous recognition of facial expressions. The resulting MT-EmotiEffNet extracts visual features that are fed into simple feed-forward neural networks.
• Score: 7.056222499095849
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we present the results of the HSE-NN team in the 4th competition on Affective Behavior Analysis in-the-wild (ABAW). The novel multi-task EfficientNet model is trained for simultaneous recognition of facial expressions and prediction of valence and arousal on static photos. The resulting MT-EmotiEffNet extracts visual features that are fed into simple feed-forward neural networks in the multi-task learning challenge. We obtain performance measure 1.3 on the validation set, which is significantly greater when compared to either performance of baseline (0.3) or existing models that are trained only on the s-Aff-Wild2 database. In the learning from synthetic data challenge, the quality of the original synthetic training set is increased by using the super-resolution techniques, such as Real-ESRGAN. Next, the MT-EmotiEffNet is fine-tuned on the new training set. The final prediction is a simple blending ensemble of pre-trained and fine-tuned MT-EmotiEffNets. Our average validation F1 score is 18% greater than the baseline convolutional neural network.

Related papers

• Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification [0.0]
  We first pre-train the model with self-supervision to enable it to learn common feature expressions on a large amount of unlabeled data. Then fine-tune it on the few-shot dataset Mini-ImageNet to improve the model's accuracy and generalization ability under limited data.
  arXiv  Detail & Related papers  (2024-11-19T01:01:56Z)
• HSEmotion Team at the 7th ABAW Challenge: Multi-Task Learning and Compound Facial Expression Recognition [16.860963320038902]
  We describe the results of the HSEmotion team in two tasks of the seventh Affective Behavior Analysis in-the-wild (ABAW) competition. We propose an efficient pipeline based on frame-level facial feature extractors pre-trained in multi-task settings. We ensure the privacy-awareness of our techniques by using the lightweight architectures of neural networks.
  arXiv  Detail & Related papers  (2024-07-18T05:47:49Z)
• HSEmotion Team at the 6th ABAW Competition: Facial Expressions, Valence-Arousal and Emotion Intensity Prediction [16.860963320038902]
  We study the possibility of using pre-trained deep models that extract reliable emotional features without the need to fine-tune the neural networks for a downstream task. We introduce several lightweight models based on MobileViT, MobileFaceNet, EfficientNet, and DFNDAM architectures trained in multi-task scenarios to recognize facial expressions. Our approach lets us significantly improve quality metrics on validation sets compared to existing non-ensemble techniques.
  arXiv  Detail & Related papers  (2024-03-18T09:08:41Z)
• Video and Synthetic MRI Pre-training of 3D Vision Architectures for Neuroimage Analysis [3.208731414009847]
  Transfer learning involves pre-training deep learning models on a large corpus of data for adaptation to specific tasks. We benchmarked vision transformers (ViTs) and convolutional neural networks (CNNs) with varied upstream pre-training approaches. The resulting pre-trained models can be adapted to a range of downstream tasks, even when training data for the target task is limited.
  arXiv  Detail & Related papers  (2023-09-09T00:33:23Z)
• On the Soft-Subnetwork for Few-shot Class Incremental Learning [67.0373924836107]
  We propose a few-shot class incremental learning (FSCIL) method referred to as emphSoft-SubNetworks (SoftNet). Our objective is to learn a sequence of sessions incrementally, where each session only includes a few training instances per class while preserving the knowledge of the previously learned ones. We provide comprehensive empirical validations demonstrating that our SoftNet effectively tackles the few-shot incremental learning problem by surpassing the performance of state-of-the-art baselines over benchmark datasets.
  arXiv  Detail & Related papers  (2022-09-15T04:54:02Z)
• Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics [85.31710759801705]
  Current practice requires expensive computational costs in model training for performance prediction. We propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
  arXiv  Detail & Related papers  (2022-01-11T20:53:15Z)
• Efficient Self-supervised Vision Transformers for Representation Learning [86.57557009109411]
  We show that multi-stage architectures with sparse self-attentions can significantly reduce modeling complexity. We propose a new pre-training task of region matching which allows the model to capture fine-grained region dependencies. Our results show that combining the two techniques, EsViT achieves 81.3% top-1 on the ImageNet linear probe evaluation.
  arXiv  Detail & Related papers  (2021-06-17T19:57:33Z)
• Facial expression and attributes recognition based on multi-task learning of lightweight neural networks [9.162936410696409]
  We examine the multi-task training of lightweight convolutional neural networks for face identification and classification of facial attributes. It is shown that it is still necessary to fine-tune these networks in order to predict facial expressions. Several models are presented based on MobileNet, EfficientNet and RexNet architectures.
  arXiv  Detail & Related papers  (2021-03-31T14:21:04Z)
• MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption [69.76837484008033]
  An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. Our approach significantly improves the state-of-the-art results on the CIFAR-10-Corrupted image classification benchmark.
  arXiv  Detail & Related papers  (2021-03-30T09:33:38Z)
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration [74.5509794733707]
  We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution. Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs. Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
  arXiv  Detail & Related papers  (2021-02-17T18:59:28Z)
• Fast accuracy estimation of deep learning based multi-class musical source separation [79.10962538141445]
  We propose a method to evaluate the separability of instruments in any dataset without training and tuning a neural network. Based on the oracle principle with an ideal ratio mask, our approach is an excellent proxy to estimate the separation performances of state-of-the-art deep learning approaches.
  arXiv  Detail & Related papers  (2020-10-19T13:05:08Z)

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.