arXiv AI

Hyperbolic Hierarchical Clustering for Visual Representation Learning

The paper introduces ClusterMixer, a token mixer based on hierarchical clustering in hyperbolic space, designed to be transparent and interpretable. It forms the core of a new vision backbone called HCFormer, which incorporates multiple clustering strategies to maintain strong performance. Experiments show HCFormer surpasses existing backbones on tasks such as image classification, object detection, instance segmentation, and semantic segmentation.

arXiv Computer Vision
6d 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
arXiv Machine Learning
Aug 27

Token-Oriented Semantic Communication with Pretrained Vision Transformers

The paper introduces a token‑oriented semantic communication framework that transmits only task‑relevant image latents instead of full token embeddings, reducing communication cost and improving interoperability. It leverages a spatial alignment between vision transformer patch tokens and learned image compression latents, enabling token‑level relevance estimation and selective transmission. Experiments on ImageNet demonstrate a superior rate–accuracy trade‑off compared to existing semantic communication methods and hand‑crafted codecs.

By Jiwoong Im, Minwoo Kim, Jaeho Lee, Yo-Seb Jeon, Yongjune Kim
arXiv Computer Vision
Aug 27

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

ARGenSeg introduces an autoregressive generation-based approach for image segmentation that integrates seamlessly with multimodal large language models (MLLMs). Unlike prior methods that use boundary points or dedicated segmentation heads, ARGenSeg generates dense masks directly through visual token output and detokenization via a universal VQ‑VAE, enabling fine‑grained pixel‑level perception. The framework employs a next‑scale‑prediction strategy to parallelize token generation, resulting in faster inference while outperforming state‑of‑the‑art segmentation models on multiple datasets.

By Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou
arXiv AI
Jul 7

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models

arXiv:2607. 04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model.

By Riccardo Renzulli, Gabriele Spadaro, Shruthi Gowda, Alaa Eddine Mazouz, Van-Tam Nguyen
arXiv Machine Learning
Aug 12

UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations

arXiv:2608. 10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.

By Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca, Ethan Fetaya, Yftah Ziser, Gal Chechik, Haggai Maron
arXiv Machine Learning
Jun 9

Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models

arXiv:2604. 06893v3 Announce Type: replace-cross Abstract: Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations.

By Tom Devynck, Bilal Faye, Djamel Bouchaffra, Nadjib Lazaar, Hanane Azzag, Mustapha Lebbah