轻量模型提升眼神估计精度，参数减少八成以上
Multi-task Gaze Estimation Via Unidirectional Convolution
- 采用单向卷积扩展感受野，降低计算开销
- 在两个数据集上准确率分别提升2.75%和1.71%
- 适合移动端或实时眼神估计场景
在眼神估计任务中，使用轻量级主干网络常导致性能显著下降，主要原因是轻量级网络的特征通道数较少，模型表达能力受限。为提升轻量级模型在眼神估计中的表现，本文提出Multitask-Gaze网络模型，包含单向卷积（UC）、空间与通道注意力（SCA）、全局卷积模块（GCM）和多任务回归模块（MRM）。UC不仅大幅减少参数量和浮点运算次数（FLOPs），还扩展感受野，增强长距离建模能力；SCA突出与眼神相关特征，抑制无关特征；GCM替代池化层，避免信息丢失；MRM提升各任务精度并加强任务间关联性。实验表明，相比先进方法SUGE，Multitask-Gaze在MPIIFaceGaze和Gaze360数据集上的准确率分别提升1.71%和2.75%，同时参数量减少75.5%，FLOPs降低86.88%。
原文摘要 · Abstract (English)
Using lightweight models as backbone networks in gaze estimation tasks often results in significant performance degradation. The main reason is that the number of feature channels in lightweight networks is usually small, which makes the model expression ability limited. In order to improve the performance of lightweight models in gaze estimation tasks, a network model named Multitask-Gaze is proposed. The main components of Multitask-Gaze include Unidirectional Convolution (UC), Spatial and Channel Attention (SCA), Global Convolution Module (GCM), and Multi-task Regression Module(MRM). UC not only significantly reduces the number of parameters and FLOPs, but also extends the receptive field and improves the long-distance modeling capability of the model, thereby improving the model performance. SCA highlights gaze-related features and suppresses gaze-irrelevant features. The GCM replaces the pooling layer and avoids the performance degradation due to information loss. MRM improves the accuracy of individual tasks and strengthens the connections between tasks for overall performance improvement. The experimental results show that compared with the State-of-the-art method SUGE, the performance of Multitask-Gaze on MPIIFaceGaze and Gaze360 datasets is improved by 1.71% and 2.75%, respectively, while the number of parameters and FLOPs are significantly reduced by 75.5% and 86.88%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。