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:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
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.
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.
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.
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.
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.
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.
arXiv:2608. 19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results.
OptiModNet is a lightweight UNet‑Transformer hybrid designed for optic disc and cup segmentation. It incorporates grouped‑query and channel attention across multiple stages, along with an Aggregated Pyramid Loss to improve gradient flow and structural consistency. Evaluated on the REFUGE2 dataset, it surpasses existing methods by over 2.5 % while using only 3.73 GFLOPs and 1.93 M parameters.
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.