Zhiqiang Tao, Huan Wang, Yun Fu, Yulun Zhang, Jiamian Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further deployment on edge devices. This work investigates the potential of network pruning for super-resolution to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. Two main challenges remain in applying pruning methods for SR. First, the widely-used filter pruning technique reflects limited granularity and restricted adaptability to diverse network structures. Second, existing pruning methods generally operate upon a pre-trained network for the sparse structure determination, hard to get rid of dense model training in the traditional SR paradigm. To address these challenges, we adopt unstructured pruning with sparse models directly trained from scratch. Specifically, we propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly initialized network at each iteration and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly. We observe that the proposed ISS-P can dynamically learn sparse structures adapting to the optimization process and preserve the sparse model's trainability by yielding a more regularized gradient throughput. Experiments on benchmark datasets demonstrate the effectiveness of the proposed ISS-P over diverse network architectures. Code is available at https://github.com/Jiamian-Wang/ Iterative-Soft-Shrinkage-SR
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.09650")
get_code_for_paper("2303.09650")
have("2303.09650")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.09650.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.09650)
Connect an agent — have() is free.