Deep Neural Network Compression for Image Classification and Object Detection

Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real-time image classification or object detection. In this work, we propose a network-agnostic model compression method infused with a novel dynamical clustering approach to reduce the computational cost and memory footprint of deep neural networks. We evaluated our new compression method on five different state-of-the-art image classification and object detection networks. In classification networks, we pruned about 95% of network parameters. In advanced detection networks such as YOLOv3, our proposed compression method managed to reduce the model parameters up to 59.70% which yielded 110X less memory without sacrificing much in accuracy.

Asif, AhrazVolvo Technology AB, VGTT, Gothenburg, Sweden (författare)
Baci, SaimirVolvo Technology AB, VGTT, Gothenburg, Sweden (författare)
Cavdar, SelcukVolvo Technology AB, VGTT, Gothenburg, Sweden (författare)
Erdal Aksoy, Eren,1982-Högskolan i Halmstad,CAISR Centrum för tillämpade intelligenta system (IS-lab),Volvo Technology AB, VGTT, Gothenburg, Sweden(Swepub:hh)ereaks (författare)
Volvo Technology AB, VGTT, Gothenburg, SwedenCAISR Centrum för tillämpade intelligenta system (IS-lab) (creator_code:org_t)

Av författaren/redakt...: Tzelepis, Georgi ...; Asif, Ahraz; Baci, Saimir; Cavdar, Selcuk; Erdal Aksoy, Ere ...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Kommunikationssy ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.