Spectral classification plays a crucial role in the analysis of astronomical data.
Currently, stellar spectral classification primarily relies on one-dimensional (1D) spectra and
necessitates a sufficient signal-to-noise ratio (SNR). However, in cases where the SNR is low,
obtaining valuable information becomes impractical. In this paper, we propose a novel model
called DRC-Net (Double-branch celestial spectra classification network based on residual
mechanisms) for stellar classification, which operates solely on two-dimensional(2D) spec tra. The model consists of two branches that use 1D convolutions to reduce the dimensionality
of the 2D spectral composed of both blue and red arms. In the following the features extracted
from both branches are fused, and the fused result undergoes further feature extraction before
being fed into the classifier for final output generation. The dataset is from the Large Sky Area
Multi-Object Fiber Spectroscopic Telescope (LAMOST), comprising 15,680 spectra of F, G,
and K type. The prepocessing process includes normalization and early stopping mechanism.
The experimental results demonstrate that the proposed DRC-Net achieved remarkable clas sification precision of 93.0%, 83.5%, and 86.9% for F, G, and K type, respectively, surpassing
the performance of 1D spectral classification methods. Furthermore, different SNR intervals
are tested to judge the classification ability of DRC-Net. The results reveal that DRC-Net, as
a 2D spectral classification model, can deliver superior classification outcomes for the spectra
with low SNRs. These experimental findings not only validate the efficiency of DRC-Net but
also confirm the enhanced noise resistance ability exhibited by 2D spectra.