Small-sample learning with salient-region detection and center neighbor loss for insect recognition in real-world complex scenarios

Abstract Most real-world scenarios face the problems of small-sample learning and fine-grained recognition. For many rare insect classes, collecting a large number of training samples is infeasible or even impossible. In contrast, humans are able to recognize a new object class with little supervision. This motivates us to address the problems of small-sample recognition and fine-grained recognition for insects by combining recognition and localization; this can provide an effective remedy for data scarcity and the two techniques can bootstrap from each other. In this paper, we propose a saliency-detection model to localize the key regions that have the largest discriminative features for fine-grained insect classification. The learner learns to predict foreground and background masks for such localization, having been trained on a training set annotated with bounding boxes. Additionally, to further generate discriminative features, a center neighbor loss function is used to construct a robust feature-space distribution. The proposed model is trained end-to-end on our small-sample learning dataset, which comprises 220 insect categories from a real-world complex environment. Compared with the method using prototypical networks, the proposed method achieves a superior performance, with a mean recognition rate (top-5 accuracy) of 57.65%, and can effectively recognize insects under small-sample and complex-scene conditions.