arXiv Computer Vision By Phat Nguyen, Xue Geng, Kaixin Xu, Wang Zhe, Xulei Yang, Ngai-Man Cheung

Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging

Read the original on arXiv Computer Vision →

The paper introduces a holistic framework that jointly optimizes architecture, token, and bit-width for Vision Transformers (ViTs). It uses Neural Architecture Search (AutoFormer) to find compact backbones, token merging (ToMe) to reduce information processing, and fp16 mixed‑precision inference to accelerate operations. Experiments on ImageNet‑1K and a real‑world 3D X‑ray semiconductor defect dataset show over 10× improvements in throughput and reductions in parameters, FLOPs, and energy while preserving accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
1d ago

Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM

The paper studies Graph-Guided Token Merging (G2TM), a module that reduces token count in Vision Transformers. It evaluates G2TM across multiple segmentation frameworks and decoder types, finding that its performance gains are tied to the encoder rather than the decoder. The authors report consistent reductions in GFLOPs (22‑47%) and throughput improvements (up to 74%) on ADE20K, with optimal hyperparameters depending mainly on backbone pre‑training and target dataset.

By Victor Bercy, Martyna Poreba, Michal Szczepanski, Samia Bouchafa