arXiv Computer Vision August 25, 2026 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.

arXiv Machine Learning

Aug 14

MergeOver: Post-Training Token Merging for Recursive Vision Transformers

arXiv:2608. 13141v1 Announce Type: cross Abstract: Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational complexity, severely limiting their deployment on resource-constrained edge hardware.

By Junseo Kim, Uraz Odyurt, Amirreza Yousefzadeh

llms computer-vision efficiency

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

llms computer-vision

arXiv AI

3d ago

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

arXiv Computer Vision

4d ago

Multi-Scale Fruit Capsules: Dilated Convolutions and Dynamic Routing for In-the-Wild Explainable Fruit Recognition

arXiv:2608.21454v1 Announce Type: new Abstract: The same fruit appears in a bunch, unpicked, peeled, bagged in plastic, or sliced on a dish, so automated fruit classification in the wild (AFCW) must...

By Subhankar Chattoraj, Sawon Pratiher, Samiran Das, Hubert Konik

fine-tuning

arXiv AI

Jun 3

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.

By Glenn Jocher, Jing Qiu, Mengyu Liu, Shuai Lyu, Fatih Cagatay Akyon, Muhammet Esat Kalfaoglu

llms computer-vision

arXiv AI

Jun 2

On the Limits of Token Reduction for Efficient Unified Vision Language Training

arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.

By Siyi Chen, Weiming Zhuang, Jingtao Li, Lingjuan Lv

llms multimodal

One email a morning, machine-written

Related stories

MergeOver: Post-Training Token Merging for Recursive Vision Transformers

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

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

Multi-Scale Fruit Capsules: Dilated Convolutions and Dynamic Routing for In-the-Wild Explainable Fruit Recognition

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

On the Limits of Token Reduction for Efficient Unified Vision Language Training