paper-with-me

Papers

SASA: Saliency-Aware Self-Adaptive Snapshot Compressive Imaging

2023-12-30 · Yaping Zhao, Edmund Y. Lam

The ability of snapshot compressive imaging (SCI) systems to efficiently capture high-dimensional (HD) data depends on the advent of novel optical designs to sample the HD data as two-dimensional (2D) compressed measurements. Nonetheless, the traditional SCI scheme is fundamentally limited, due to the complete disregard for high-level information in the sampling process. To tackle this issue, in this paper, we pave the first mile toward the advanced design of adaptive coding masks for SCI. Specifically, we propose an efficient and effective algorithm to generate coding masks with the assistance of saliency detection, in a low-cost and low-power fashion. Experiments demonstrate the effectiveness and efficiency of our approach. Code is available at: https://github.com/IndigoPurple/SASA

📄 PDF Abstract BibTeX arXiv:2401.00875

Code (1)

indigopurple/sasa 공식 구현

Tasks

Saliency Detection

Similar Papers 제목 키워드 기반

SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track

2026-03-28 · Dengxian Gong, Quanzhu Niu, Shihao Chen, Yuanzheng Wu 외 arxiv

Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions (referring & reasoning motion expressio…

Referring Video Object Segmentation

Understanding Long Programming Languages with Structure-Aware Sparse Attention

2022-05-27 · Tingting Liu, Chengyu Wang, Cen Chen, Ming Gao 외

Programming-based Pre-trained Language Models (PPLMs) such as CodeBERT have achieved great success in many downstream code-related tasks. Since the memory and computational complexity of self-attention in the Transformer…

Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution

2023-09-27 · Ying Sun, HengShu Zhu, Hui Xiong

Self-interpreting neural networks have garnered significant interest in research. Existing works in this domain often (1) lack a solid theoretical foundation ensuring genuine interpretability or (2) compromise model expr…

Large Language Models can be Strong Self-Detoxifiers

2024-10-04 · Ching-Yun Ko, Pin-Yu Chen, Payel Das, Youssef Mroueh 외

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language mo…

Language Modelling

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models

2025-07-29 · Wanying Wang, Zeyu Ma, Han Zheng, Xin Tan 외 arxiv

Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety under…