Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition

  title={Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition},
  author={Delian Ruan and Yan Yan and Shenqi Lai and Zhenhua Chai and Chunhua Shen and Hanzi Wang},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Delian RuanYan Yan Hanzi Wang
  • Published 12 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network… 

Figures and Tables from this paper

Facial Expression Recognition Based on Squeeze Vision Transformer

This paper proposes Squeeze ViT, a method for reducing the computational complexity by reducing the number of feature dimensions while increasing the FER performance by concurrently combining global and local features.

Self-Paced Label Distribution Learning for In-The-Wild Facial Expression Recognition

A play-and-plug method of self-paced label distribution learning (SPLDL) for in-the-wild FER, which first learns easy samples with reliable label distributions and gradually steps to complex ones, effectively suppressing the negative impact introduced by noisy samples and unreliable label distributions.

FaceTopoNet: Facial Expression Recognition using Face Topology Learning

FaceTopoNet is proposed, an end-to-end deep model for facial expression recognition, which is capable of learning an effective tree topology of the face and is more robust against occlusions in comparison to other leading methods in the area.

A comprehensive review of facial expression recognition techniques

The paper provides a comprehensive review of recent advancements in algorithm development, presents the overall findings performed over the past decades, discusses their advantages and constraints, and explores the transition from the laboratory-controlled environment to challenging real-world (in-the-wild) conditions.

Adaptive Graph-Based Feature Normalization for Facial Expression Recognition

This work proposes an Adaptive Graph-based Feature Normalization (AGFN) method to protect FER models from data uncertainties by normalizing feature distributions with the association of expressions, and proposes a Poisson graph generator to adaptively construct topological graphs for samples in each mini-batches via a sampling process.

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

This paper proposes a novel cascaded decomposition network (CDNet), which cascades several learn-to-decompose modules with shared parameters based on a sequential decomposition mechanism, to obtain a transferable feature space in the cross-domain few-shot learning (FSL) setting.

Disentangled-region non-local neural network for facial expression recognition

This work proposes a disentangled-region non-local (DRNL) neural network, which can capture the long-range dependencies directly by calculating the interaction between the pixel and the region, not limited to the adjacent pixels, to maintain more information.

POSTER V2: A simpler and stronger facial expression recognition network

This paper improves POSTER V1 in three directions: cross-fusion, two-stream, and multi-scale feature extraction, which achieves the SOTA FER performance with the minimum computational cost.

Can Hierarchical Transformers Learn Facial Geometry?

This work proposes using a hierarchical transformer architecture as a means of capturing a robust representation of facial geometry and demonstrates the versatility of this approach by using this transformer as a backbone to support three facial representation problems: face anti-spoofing, facial expression representation, and deepfake detection.

Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition

Two attentive pooling (AP) modules to pool noisy features directly and intuitively reduce the computational cost while boosting the performance by pursuing the most discriminative features are presented.



Reliable Crowdsourcing and Deep Locality-Preserving Learning for Unconstrained Facial Expression Recognition

A new deep locality-preserving convolutional neural network (DLP-CNN) method that aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatter is proposed.

Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark

A person independent training and testing protocol for expression recognition as part of the BEFIT workshop is proposed and a new static facial expression database Static Facial Expressions in the Wild (SFEW) is presented.

Web-based database for facial expression analysis

The MMI facial expression database is presented, which includes more than 1500 samples of both static images and image sequences of faces in frontal and in profile view displaying various expressions of emotion, single and multiple facial muscle activation.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Deep Disturbance-Disentangled Learning for Facial Expression Recognition

This paper proposes a novel Deep Disturbance-disentangled Learning (DDL) method for FER that is capable of simultaneously and explicitly disentangling multiple disturbing factors by taking advantage of multi-task learning and adversarial transfer learning.

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Self-Cure Network suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over FER dataset to weight each sample in training with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group.

Identity- and Pose-Robust Facial Expression Recognition through Adversarial Feature Learning

An adversarial feature learning method to address both pose variations or identity bias and the superiority of the proposed method to state-of-the-art work is demonstrated.

Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition

A novel Region Attention Network (RAN), to adaptively capture the importance of facial regions for occlusion and pose variant FER, and a region biased loss to encourage high attention weights for the most important regions.

Deep multi-path convolutional neural network joint with salient region attention for facial expression recognition