Skip to main content

Table 2 Main properties of different channel pruning techniques

From: Exploiting prunability for person re-identification

Strategy Methods Criteria
Prune in one step L1 [33] Weights: \( S_{j}=\sum \left | w_{k} \right | \)
  Redundant channels [67] Weights: \(SIM_{C}(\mathbf {W}_{i},\mathbf {W}_{j}) = \frac {\mathbf {W}_{i}\boldsymbol {\cdot } \mathbf {W}_{j}}{\left \| \mathbf {W}_{i} \left \| \boldsymbol {\cdot } \right \| \mathbf {W}_{j} \right \|}\)
  Entropy [34] Feature maps: \(E_{j} = -\sum _{a=1}^{m}\left (p_{a}log(p_{a})\right)\)
Prune iteratively Taylor [32] Feature maps: \(\left | \Delta C(\mathbf {H}_{i,j}) \right | = \left | \frac {\delta C}{\delta \mathbf {H}_{i,j}} \mathbf {H}_{i,j}\right |\)
  FPGM [68] Weights: \(\phantom {\dot {i}\!}\mathbf {W}_{i,j^{\ast }} \in {argmin}_{j^{\ast } \in R^{n_{{in}} \times k * \times k}} \sum _{j^{\prime } \in [1, n_{{out}}]} ||x - \mathbf {W}_{i,j^{\prime }}||_{2}\)
Prune iteratively with regularization Play and Prune [69] Weights: \(S{_{j}}=\sum \left | w_{k} \right |\)
  Auto-Balance [70] Weights: \(S{_{j}}=\sum \left | w_{k} \right |\)
Prune iteratively, min reconstruction error ThiNet Feature maps: \(\mathbf {H}_{i+1,j} = \sum _{j=1}^{C} \sum _{k=1}^{K} \sum _{k=1}^{K} \mathbf {W}_{i,j,k,k}*\mathbf {H}_{i,j}\)
  Channel pruning [35] Feature maps: \({\underset {\beta,\mathbf {W}}{\arg \min } \tfrac {1}{2N}\left \| \mathbf {H}_{i+1,j} - \sum _{j=1}^{n} \beta _{i,j} \mathbf {H}_{i,j} \mathbf {W}_{i,j} \right \|_{F}^{2}+ \lambda \left \| \beta \right \|_{1} }\)
Prune progressively PSFP [36] Weights: \(S{_{j}}=\sum \left | w_{k} \right |_{2}\)