There are thousands varieties of silkworm pupae in China. The existing recognition models are unable to meet the needs for the intelligent sex separation of silkworm pupae with new variety from most silkworm breeding station across the country. Re-annotating a large number of samples to build new model for each new variety will cost much time and cannot satisfy the requirement for rapid sex classification within one week. Currently, there is no research available on automated sex separation applicable to various silkworm pupa varieties. Therefore, this paper proposes an novel approach based on a pre-trained model established with a large number of labeled silkworm pupae, which employs curriculum learning and adaptive threshold updating strategy to effectively address the issue of sex identification of silkworm pupae with new varieties. Firstly, for a new variety c of silkworm pupa (either female or male) at time step \(t\) with an initial global threshold \({\tau }_{t}\) of 0.5, \({\sigma }_{t}\left(c\right)\) represents the number of unlabeled data predicted to female or male that reaches the current threshold, which can reflect the learning effects for the new variety. Then, the flexible threshold \({T}_{t}\left(c\right)\) is generated for female or male silkworm pupa with new variety. Next, the global confidence threshold \({\tau }_{t}\) is updated using exponential moving average (EMA). As learning going, the threshold gradually increases to select higher quality samples. Finally, the model is updated by computing the unsupervised loss using the updated flexible thresholds and combine with the supervised loss. Through model updating experiments involving six new varieties of silkworm pupae, the proposed method showed the performance comparable to supervised methods across all new variety of silkworm datasets, with the accuracy range of 88.33% to 97.67%, which performed better than other models such as UDA and FixMatch. SequenceMatch’s performance was almost the same with our method, but it needed 3.759 h to update the model with new species, which was much longer than our method(2.019 h). Furthermore, when the model updating experiment with silkworm pupae from different years, it reached the accuracy of 87.27% ~ 97.32%. And the experiments about public CIFAR-10 dataset further demonstrated the generalization ability and effectiveness of the proposed method with accuracy of 96.4%. This research will contribute to the intelligence and automation improvement of silkworm industry.
