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.
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.
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.
arXiv:2609.10469v1 Announce Type: new Abstract: Automated plant disease diagnosis is increasingly deployed on farmer-held devices in regions where agronomic expertise is scarce and network connectivi...
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.
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.
arXiv:2603.27519v4 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, orga...
PlantC2USeg is a deep transfer‑learning framework that uses cross‑scale consistency learning and an information‑restricted decoder to improve plant point cloud segmentation. It achieves state‑of‑the‑art performance on Soybean3D and ShapeNet Part, and demonstrates strong few‑shot generalization across species and sensing conditions. The method reduces the need for large annotated datasets and lowers adaptation overhead for new plant species.
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...
arXiv:2606. 03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware.
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
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.
The paper introduces Gated Token Recurrence (GTR), a softmax‑free recurrent vision backbone that replaces global softmax attention with gated linear attention, alternating scan directions, and enhanced SwiGLU blocks. GTR is distilled from a DINOv3 teacher using only final‑layer patch‑token alignment, and achieves strong performance on COCO object detection (58.9 box AP) with very low latency (1.908 ms on an RTX 4090). The backbone also transfers to multiple dense prediction tasks and runs efficiently on edge hardware via a specialized CUDA operator and TensorRT deployment.