In this paper, we introduce a framework ARBEx, a novel attentive feature extraction framework driven by Vision Transformer with reliability balancing to cope against poor class distributions, bias, and uncertainty in the facial expression learning (FEL) task. We reinforce several data pre-processing and refinement methods along with a window-based cross-attention ViT to squeeze the best of the data. We also employ learnable anchor points in the embedding space with label distributions and multi-head self-attention mechanism to optimize performance against weak predictions with reliability balancing, which is a strategy that leverages anchor points, attention scores, and confidence values to enhance the resilience of label predictions. To ensure correct label classification and improve the models' discriminative power, we introduce anchor loss, which encourages large margins between anchor points. Additionally, the multi-head self-attention mechanism, which is also trainable, plays an integral role in identifying accurate labels. This approach provides critical elements for improving the reliability of predictions and has a substantial positive effect on final prediction capabilities. Our adaptive model can be integrated with any deep neural network to forestall challenges in various recognition tasks. Our strategy outperforms current state-of-the-art methodologies, according to extensive experiments conducted in a variety of contexts.

翻译：本文提出框架ARBEx，一种由Vision Transformer驱动的创新注意力特征提取框架，通过可靠性平衡机制应对面部表情学习任务中的类别分布不均、偏差及不确定性。我们强化了多种数据预处理与精炼方法，结合基于窗口的交叉注意力ViT以充分挖掘数据价值。同时，在嵌入空间中利用可学习锚点、标签分布及多头自注意力机制，通过可靠性平衡策略（一种利用锚点、注意力分数和置信度增强标签预测鲁棒性的策略）优化弱预测性能。为确保正确标签分类并提升模型判别能力，我们引入锚点损失函数，促使锚点间保持较大间隔。此外，可训练的多头自注意力机制在精准识别标签方面发挥核心作用。该方法为提升预测可靠性提供关键要素，并对最终预测能力产生显著正向影响。本自适应模型可集成至任意深度神经网络，以应对各类识别任务中的挑战。多场景广泛实验证明，本策略优于现有最先进方法。