← Back to all news
arXiv Computer Vision By Le Yang, Yucheng Huang, Junyu Chen, Qi Dang, Xin Kong, Haifeng Huo, Qiang Zhao

SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition

Read the original on arXiv Computer Vision →

SAGE (Saliency‑Annealed Gated Encoder) is a Vision Transformer‑based backbone that explicitly leverages saliency, global context, and high‑frequency details through a saliency‑guided architecture, an annealing training paradigm, and a two‑stage loss transition. It achieves state‑of‑the‑art or competitive results on a wide range of dense prediction tasks, including COCO object detection and segmentation, ADE20K segmentation, TinyImageNet classification, and DIOR‑R oriented detection, all using the same backbone with task‑specific decoders. The framework is notable for being the first to deliver multi‑task SOTA performance on Huawei Ascend NPUs.

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 AI
6d ago

ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer

The paper introduces ACSAN, an All‑Convolutional Self‑Attention Network that replaces the fully‑connected matrix multiplications of Vision Transformers with convolution operations. Its core module, Dynamic Convolutional Self‑Attention (DCSA), uses multi‑scale dilated convolutions to produce Query, Key, and Value tensors, and combines spatial and channel self‑attention into a single output. Experiments on CIFAR‑10, CIFAR‑100, and ImageNet‑1k demonstrate that ACSAN attains competitive or superior classification accuracy to ViT while using comparable or fewer parameters, and ablation studies confirm the positive contribution of each component.

By Zimian Wei, Tianqi Zhang, Hengyue Pan
llmscomputer-visionbenchmarks
More like this →
arXiv AI
5d ago

LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models

LearnPrunerV2 is a fully learnable token‑pruning framework for Vision‑Language Models that replaces heuristic pruning with lightweight modules in every backbone layer. These modules estimate token importance by combining visual saliency and query relevance via a shadow token, revealing a consistent staircase redundancy pattern across layers. The method introduces Budget‑Deterministic Pruning to set fixed per‑layer budgets, achieving state‑of‑the‑art efficiency while preserving 99.8% of performance even after pruning 77.8% of visual tokens on LLaVA‑v1.5.

By Rinyoichi Takezoe, Yaqian Li, Weiren Wang, Zihao Bo, Huihong Shi, Anzhou Hou, Mo Guang, Jiale Yan, Kaiwen Long
llmsefficiencymultimodalbenchmarks
More like this →