SCMerge is a training‑free token merging technique for Vision Transformers that jointly considers feature similarity and spatial consistency when pairing tokens. The merged tokens are processed within the encoder and later reconstructed onto the original patch grid during decoding. Experiments on ADE20K, Pascal Context, and Cityscapes demonstrate that SCMerge improves the balance between segmentation accuracy and computational efficiency compared to existing methods.
By Junfeng Ren (Southern University of Science and Technology), Yi Gong (Southern University of Science and Technology), Yuan Zeng (Shenzhen Technology University)
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
By Kyumin Choi, Ikbeom Jang
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
Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders practical applications. Recent works have focused on m...
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
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
By Jordan Sassoon, Michal Szczepanski, Martyna Poreba
SetCon reformulates open-ended referring segmentation as set-level concept prediction, using LVLM-generated natural-language concepts instead of segmentation-specific tokens. It employs a hierarchical semantic decomposition that first predicts a shared set-level concept and then refines it into fine-grained concept groups aligned with target subsets. The method, supported by a two-stage annotation pipeline adding hierarchical semantic supervision, achieves state-of-the-art results on multiple image and video benchmarks, with performance gains increasing as the number of referred targets grows.
By Zhixiong Zhang, Yizhuo Li, Shuangrui Ding, Yuhang Zang, Shengyuan Ding, Long Xing, Yibin Wang, Qiaosheng Zhang, Jiaqi Wang
MaskMerge introduces a structure-aware token merging strategy for Vision Transformers that leverages coarse mask predictions to guide token fusion, preventing cross-instance token merging that plagues existing methods. In high inter-instance similarity settings such as PanNuke and iSAID, MaskMerge boosts mAP from 30.1 to 32.1 and 33.1 to 36.2 respectively, while cutting FLOPs and speeding up inference. The approach also matches state‑of‑the‑art performance on Cityscapes with fewer computations and transfers well to MAE‑pretrained backbones.
By Bavesh Balaji, Letian Jiang, Alexander Wong, David Clausi, Sirisha Rambhatla
arXiv:2607. 00687v1 Announce Type: cross Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself.
By Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov, Brian B. Moser, Andreas Dengel
arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.
By Jusheng Zhang, Xiaoyang Guo, Tongyu Mo, Qinhan Lv, Wenhao Chai, Jian Wang, Keze Wang, Liang Lin
Pixels to Tokens introduces TEAL, a token‑space efficient active learning framework that operates at the pixel level for semantic segmentation using a frozen Vision Transformer backbone. TEAL selects diverse candidate pixels via a two‑level MaxHerding strategy on multi‑layer token descriptors and refines uncertainty on a finer decoder grid, avoiding interpolation artifacts. Across multiple datasets, TEAL outperforms prior baselines under extreme label scarcity, achieving up to +24.36 mIoU with a single labeled pixel per image and reaching 97% of fully supervised performance with only ten pixels.
By Utku Cicek, Mahip Singh, Ziyao Shang, Kimathi Kaai, C Thomas, Pedro Pablo Guerrero Vela, Alexander Wong, Sirisha Rambhatla
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