ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration difficulty, and then the sparse subnetworks with different capabilities can be sampled based on predicted difficulty by performing dynamic N:M fine-grained structured pruning on base restoration networks. We further propose a novel training strategy along with two additional loss terms to stabilize training and improve performance. Experiments demonstrate that ClassPruning can help existing methods save approximately 40% FLOPs while maintaining performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RestorationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Attentive Fine-Grained Structured Sparsity for Image Restoration
Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models. Despite the outstanding performance, the heavy computation demanded by the deep models has restricted …
DeblurringImage RestorationSuper-ResolutionExploring and Evaluating Image Restoration Potential in Dynamic Scenes
In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the capt…
Image RestorationSearching for Controllable Image Restoration Networks
Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks. However, existing methods require separate inference through the entire…
4kGPUImage RestorationNeural Architecture SearchFASP: Fast and Accurate Structured Pruning of Large Language Models
The rapid increase in the size of large language models (LLMs) has significantly escalated their computational and memory demands, posing challenges for efficient deployment, especially on resource-constrained devices. S…
GPUModel CompressionPruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration
Image quality is a critical factor in delivering visually appealing content on web platforms. However, images often suffer from degradation due to lossy operations applied by online social networks (OSNs), negatively aff…
Image Restoration