Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by learning task-specific prompts. However, existing prompt-based methods heavily rely on strong pretraining (typically trained on ImageNet-21k), and we find that their models could be trapped if the potential gap between the pretraining task and unknown future tasks is large. In this work, we develop a learnable Adaptive Prompt Generator (APG). The key is to unify the prompt retrieval and prompt learning processes into a learnable prompt generator. Hence, the whole prompting process can be optimized to reduce the negative effects of the gap between tasks effectively. To make our APG avoid learning ineffective knowledge, we maintain a knowledge pool to regularize APG with the feature distribution of each class. Extensive experiments show that our method significantly outperforms advanced methods in exemplar-free incremental learning without (strong) pretraining. Besides, under strong pretraining, our method also has comparable performance to existing prompt-based models, showing that our method can still benefit from pretraining. Codes can be found at https://github.com/TOM-tym/APG

A chemical conversion coating on 5052 aluminum alloy was prepared by using K₂ZrF₆ and K₂TiF₆ as the main salts, KMnO₄ as the oxidant and NaF as the accelerant. The surface morphology, structure and composition were analyzed by SEM, EDS, FT–IR and XPS. The corrosion resistance of the conversion coating was studied by salt water immersion and polarization curve analysis. The influence of fluorosilane (FAS-17) surface modification on its antifouling property was also discussed. The results showed that the prepared conversion coating mainly consisted of AlF₃·3H₂O, Al₂O₃, MnO₂ and TiO₂, and exhibited good corrosion resistance. Its corrosion potential in 3.5 wt % NaCl solution was positively shifted about 590 mV and the corrosion current density was dropped from 1.10 to 0.48 μA cm⁻². By sealing treatment in NiF₂ solution, its corrosion resistance was further improved yielding a corrosion current density drop of 0.04 μA cm⁻². By fluorosilane (FAS-17) surface modification, the conversion coating became hydrophobic due to low-surface-energy groups such as CF₂ and CF₃, and the contact angle reached 136.8°. Moreover, by FAS-17 modification, the corrosion resistance was enhanced significantly and its corrosion rate decreased by about 25 times.