Dynamic Network Quantization for Efficient Video Inference

Kate Saenko, Richard Chen, Rameswar Panda, Aude Oliva, Rogerio Feris, Ximeng Sun

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• sunxm2357/VideoIQ

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep convolutional networks have recently achieved great success in video recognition, yet their practical realization remains a challenge due to the large amount of computational resources required to achieve robust recognition. Motivated by the effectiveness of quantization for boosting efficiency, in this paper, we propose a dynamic network quantization framework, that selects optimal precision for each frame conditioned on the input for efficient video recognition. Specifically, given a video clip, we train a very lightweight network in parallel with the recognition network, to produce a dynamic policy indicating which numerical precision to be used per frame in recognizing videos. We train both networks effectively using standard backpropagation with a loss to achieve both competitive performance and resource efficiency required for video recognition. Extensive experiments on four challenging diverse benchmark datasets demonstrate that our proposed approach provides significant savings in computation and memory usage while outperforming the existing state-of-the-art methods. Project page: https://cs-people.bu.edu/ sunxm/VideoIQ/project.html.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.10394")
get_code_for_paper("2108.10394")
have("2108.10394")

Connect an agent — have() is free.