TY - GEN 
AU - Sun H.
AU - Heuillet A.
AU - Mohr F.
AU - Tabia H.
PY - 2024
UR - http://hdl.handle.net/10818/63362
AB - Transformer models have gained popularity for their exceptional performance. However, these models still face the challenge of high inference latency. To improve the computational efficiency of such models, we propose a novel differentiable pruning...
LA - eng
PB - IEEE Journal on Selected Topics in Signal Processing
KW - Neural architecture search
KW - Neural network compression
KW - Neural network pruning
TI - DARIO: Differentiable vision transformer pruning with low-cost proxies
DO - 10.1109/JSTSP.2024.3501685
ER -