The extensive applications of spectrum analysis across various fields have rendered the traditional desktop spectrometers unable to meet the market demand for portability and instantaneity. Reducing the size of spectrometers has become a topic of interest. Based on this trend, a novel type of computational spectrometer is developed and has been widely studied owing to its unique features. Such spectrometers do not need to integrate complex mechanical or optical structures, and most of them can achieve spectrum analysis by the properties of the material itself combines with the reconstruction algorithm. Impressively, a single‐detector computational spectrometer has recently been successfully realized based on in situ modulation of material properties. This not only enables the further miniaturization of the device, but also means that the footprint‐resolution limitation which has always existed in the field of hyperspectral imaging has been broken, opening a new era of image analysis. This review summarizes the classifications and principles of various spectrometers, compares the spectrum resolution performances of different types of spectrometers, and highlights the progress of computational spectrometers, especially the revolutionary single‐detector spectrometer. It is expected that this review will provide a positive impact on expanding the boundary of spectrum analysis and move hyperspectral imaging forward.