Abstract:

In order to address the challenges of limited training data and diverse categories， a few-shot learning method was introduced. In view of the problems existing in dense object counting methods， such as unclear boundaries and spatial inconsistency of dense objects as well as weak generalization capability of model， a few-shot Similarity Matching Feature Enhancement dense object counting Network （SMFENet） was proposed. Firstly， image features were extracted through the feature extraction module， and sample features were aligned using ROI Align. Secondly， a Similarity Comparison Feature Enhancement Module （SCFEM） was designed to calculate similarity between sample features and image features， resulting in a similarity graph. This graph was used as weighting coefficients to enhance the image features adaptively with the sample features， so as to obtain the final enhanced features focusing more on regions with features similar to the sample features. At the same time， methods such as internal feature enhancement， internal scale enhancement and information fusion were employed to solve the problems of unclear boundaries and spatial inconsistency of dense objects. Finally， a density map was generated using the density prediction module. Additionally， the content-aware annotation method was used to generate high-quality Ground-Truth density maps to further improve the model accuracy. During test， the network was adjusted by adaptive loss to generalize to new categories. Experimental results on FSC-147 dataset and CARPK dataset show that compared with the existing few-shot counting methods， the proposed model has the Mean Absolute Error （MAE） reduced to 13.82 and Root Mean Squared Error （RMSE） reduced to 45.91， compared with class-specific counting method， the proposed model has the MAE reduced to 4.16 and RMSE reduced to 5.91. The above fully proves that SMFENet model can achieve good results in improving the accuracy and robustness of counting， demonstrates the practical application value of the model.

Key words: dense object counting, few-shot learning, density prediction, similarity matching feature enhancement

摘要：

为了解决训练数据有限且类别多的问题，引入小样本学习方法。针对现有密集目标计数方法中存在的密集物体边界不清晰、空间不一致性和模型泛化能力弱等问题，提出一种小样本相似性匹配特征增强密集目标计数网络（SMFENet）。首先，通过特征提取模块提取图像特征，并使用ROI Align方法对齐样例特征；其次，设计相似性比较特征增强模块（SCFEM）计算样例特征和图像特征的相似度，得到相似度图，并将该图作为加权系数用样例特征自适应地增强图像特征，使最终得到的增强特征更关注与样例特征相似的区域；同时，采用内部特征增强、内部尺度增强以及信息合并等方法解决密集物体边界不清晰和空间不一致性问题；最后，利用密度预测模块生成密度图。此外，采用内容感知标注法生成高质量Ground-Truth密度图，以进一步提升模型的准确性。测试时，通过自适应损失调整网络使网络泛化到新类别上。在FSC-147数据集和CARPK数据集上的实验结果表明，与现有的小样本目标计数方法相比，所提模型的平均绝对误差（MAE）降低到13.82，均方根误差（RMSE）降低到45.91；与特定类别计数方法相比，所提模型的MAE降低到4.16，RMSE降低到5.91。以上充分证明SMFENet模型在提高计数的准确性和鲁棒性等方面能取得较好的效果，展示了该模型的实际应用价值。

关键词: 密集目标计数, 小样本学习, 密度预测, 相似性匹配特征增强