Accurate Quantization for Gait Representation Learning

ArXi:2405.13859v3 Announce Type: replace Existing deep learning methods have made significant progress in gait representation learning. Quantization can facilitate the application of gait models as a model-agnostic general compression technique. Typically, appearance-based models binarize inputs into silhouette sequences. However, mainstream quantization methods prioritize minimizing task loss over quantization error, which is detrimental to gait representation learning with binarized inputs.