← Back to all news
arXiv Computer Vision By Yang Chen, Canyu Shen, Xinzhe Rao, Yuanyi Yan, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu

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

Read the original on arXiv Computer Vision →

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.

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.

Related stories

arXiv Computer Vision
Sep 4

ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers

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.

By Ali Hojjat, Janek Haberer, Olaf Landsiedel
llmscomputer-visionefficiency
More like this →
arXiv Computer Vision
Aug 25

SAM3Dual: A 3rd Place Solution to the MOSEv2 Track, 8th LSVOS Challenge

SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.

By JeongRae Kim, Chaehyun Kim, Changwon Lim
computer-visionfine-tuning
More like this →