← Back to all news
arXiv Computer Vision By Simon Rav\'e, Pejman Rasti, David Rousseau

How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?

Read the original on arXiv Computer Vision →

The paper evaluates how well Vision Transformers (ViTs) can handle token merging techniques—specifically ToMe and Mutual Pair Merging—across wheat phenotyping tasks such as growth-stage classification, wheat-head detection, and wheat-organ segmentation. It benchmarks task quality, throughput, token count, and GPU memory usage, including tests on a Raspberry Pi 5. Results show that classification is highly tolerant to token merging, whereas detection and segmentation suffer due to factors like repeated instances, thin organs, dense boundaries, and runtime overhead, and that optimized attention backends can negate apparent speed gains.

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.

Related stories

arXiv Computer Vision
Sep 17

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
llmscomputer-visionefficiencybenchmarks
More like this →
arXiv AI
Aug 12

A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa

arXiv:2608. 11053v1 Announce Type: cross Abstract: The application of computer vision in agriculture has shown significant potential for improving crop monitoring and precision farming.

By Ismail Ismail Tijjani, Sunusi Muhammad Ibrahim, Amina Ibrahim Khaleel, Lanre Olusegun Akinola, Fatima Isa Jibrin, Muhammad Bashir Aliyu, Abdullahi Abdussalam Dalhat, Abdullahi Suiudeen
llmscomputer-vision
More like this →
arXiv AI
Aug 26

STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification

STA‑Net is a lightweight neural network designed for plant disease classification on edge devices. It combines a training‑free neural architecture search (DeepMAD) to build an efficient backbone with a novel Shape‑Texture Attention Module (STAM) that separates shape and texture processing using deformable convolutions and a Gabor filter bank. On the CCMT plant disease dataset, STA‑Net achieved 89.00% accuracy and 88.96% F1 score with only 401K parameters and 51.1M FLOPs.

By Zongsen Qiu, Jianjun Wang, Yue Zhou, Zibo Zhou, Rui Chen
benchmarks
More like this →