arXiv Computer Vision By Ali Hojjat, Janek Haberer, Olaf Landsiedel

ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers

Read the original on arXiv Computer Vision →

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.

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 Computer Vision.

arXiv Computer Vision
1d 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 Computer Vision
Sep 1

GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction

GramLoop is a training‑free framework that enhances frozen DINOv3 dense‑prediction models under distribution shift by adding inference computation within the visual backbone. It replays a short transformer window and uses final‑layer cosine‑Gram consistency to control each replay, propagating proposals through the frozen suffix and accepting them via a patchwise gate. Across object detection and semantic segmentation tasks, GramLoop improves performance on all five shifted benchmarks, notably raising COCO‑O mAP by +0.252 and Effective Robustness by +0.250 while maintaining clean ADE20K accuracy.

By Yang Chen, Canyu Shen, Xinzhe Rao, Yuanyi Yan, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu