Serious information loss often occurs when the input data undergoes the layer-by-layer feature extraction process through deep neural networks. In small-target detection tasks, this problem becomes more serious. The existing theory holds that the information bottleneck leads to the decrease of an algorithm’s recognition rate. In order to improve the precision of small-target recognition, PGI-ViMamba is proposed in this paper to resist the information attenuation of a neural network model. The model mainly uses Multi-Level Attention-Gated Programmable Gradient Information (MLAG PGI) and SPD-Conv-VSS module. Specifically, the backbone uses an improved VSS module as a feature extractor and uses an auxiliary branch similar to YOLOv9. This neural network structure ensures that the neural network retains the feature information of the small target in the process of forward propagation while reducing the model parameters. Another advantage is that the MLAG PGI acts as a reversible branch, providing reliable gradient information. Experiments show the effectiveness of the algorithm. Compared with state-of-the-art (SOTA) models, the proposed method achieves improvements of 1.1% and 2.1% in small-target recognition precision on the VisDrone and DOTA-v1.5 datasets, respectively, with no significant decline in recall rates. Additionally, ablation experiments validate the effectiveness of the MLAG PGI and SPD-Conv-VSS modules.