arXiv Machine Learning July 27, 2026 By Yu Wang, Hongyu Yang

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

Read the original on arXiv Machine Learning →

arXiv:2607. 22068v1 Announce Type: cross Abstract: Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations.

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 Machine Learning.

arXiv Machine Learning

Sep 22

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining

arXiv:2607.22068v2 Announce Type: replace-cross Abstract: Multi-branch architectures and CNN-Transformer fusion are widely believed to improve vehicle re-identification (Re-ID) by combining complemen...

By Yu Wang, Hongyu Yang

llms rag benchmarks

arXiv Machine Learning

Jul 14

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification

arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.

By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig

llms diffusion

arXiv Computer Vision

Sep 16

CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection

arXiv:2608.06205v2 Announce Type: replace Abstract: Multispectral object detection combines visible and thermal imagery to improve perception under challenging illumination and environmental conditio...

By Nima Hatami, Karim Faez, Saeed Sharifian, Hamidreza Amindavar

computer-vision

arXiv Computer Vision

2d ago

Subtoken Vision Transformer for Fine-grained Recognition

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...

By Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu

llms computer-vision nlp

arXiv AI

4d ago

FM-ReID: Selective Competitive Token Routing for Object Re-Identification

arXiv:2609.36560v1 Announce Type: cross Abstract: Object re-identification (ReID) faces a recurring challenge: different identities can share highly similar global appearances, while the cues that di...

By Zhiqi Li, Xiaowei Zhou, Zeyuan Sun, Feng Gao, Junyu Dong

benchmarks

Hugging Face Trending Papers

5d ago

FM-ReID: Selective Competitive Token Routing for Object Re-Identification

Object re-identification (ReID) faces a recurring challenge: different identities can share highly similar global appearances, while the cues that distinguish them are localized, heterogeneous, and vi...

benchmarks

One email a morning, machine-written

Related stories

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification

CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection

Subtoken Vision Transformer for Fine-grained Recognition

FM-ReID: Selective Competitive Token Routing for Object Re-Identification

FM-ReID: Selective Competitive Token Routing for Object Re-Identification