REVIEW 1 cited by
QwT-v2: Practical, Effective and Efficient Post-Training Quantization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Network quantization is arguably one of the most practical network compression approaches for reducing the enormous resource consumption of modern deep neural networks. They usually require diverse and subtle design choices for specific architecture and tasks. Instead, the QwT method is a simple and general approach which introduces lightweight additional structures to improve quantization. But QwT incurs extra parameters and latency. More importantly, QwT is not compatible with many hardware platforms. In this paper, we propose QwT-v2, which not only enjoys all advantages of but also resolves major defects of QwT. By adopting a very lightweight channel-wise affine compensation (CWAC) module, QwT-v2 introduces significantly less extra parameters and computations compared to QwT, and at the same time matches or even outperforms QwT in accuracy. The compensation module of QwT-v2 can be integrated into quantization inference engines with little effort, which not only effectively removes the extra costs but also makes it compatible with most existing hardware platforms.
Forward citations
Cited by 1 Pith paper
-
YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association
A YOLOv8 detector trained on overlapping slices plus an OC-SORT tracker with EMA motion direction and expanded IoU distance penalty achieves 55.205 SO-HOTA on the SMOT4SB public test set.
Discussion (0). Sign in to comment.