paper-with-me

Papers

MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation

2025-04-10 · Nico Catalano, Stefano Samele, Paolo Pertino, Matteo Matteucci

Current Few Shot Segmentation literature lacks a mask selection method that goes beyond visual similarity between the query and example images, leading to suboptimal predictions. We present MARS, a plug-and-play ranking system that leverages multimodal cues to filter and merge mask proposals robustly. Starting from a set of mask predictions for a single query image, we score, filter, and merge them to improve results. Proposals are evaluated using multimodal scores computed at local and global levels. Extensive experiments on COCO-20i, Pascal-5i, LVIS-92i, and FSS-1000 demonstrate that integrating all four scoring components is crucial for robust ranking, validating our contribution. As MARS can be effortlessly integrated with various mask proposal systems, we deploy it across a wide range of top-performer methods and achieve new state-of-the-art results on multiple existing benchmarks. Code will be available upon acceptance.

📄 PDF Abstract BibTeX arXiv:2504.07942

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

2025-09-17 · Peng Xu, Shengwu Xiong, Jiajun Zhang, Yaxiong Chen 외 arxiv

This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to fo…

Visual Question AnsweringMultimodal ReasoningVisual ReasoningVisual Grounding

Harnessing Textual Refusal Directions for Multimodal Safety

2026-06-30 · Moreno D'Incà, Nicu Sebe, Massimiliano Mancini arxiv

To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space. Both strategies are less feasible in Multimodal LLMs (MLLMs) as they …

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

2025-10-12 · Zihan Zhang, Xize Cheng, Zhennan Jiang, Dongjie Fu 외 arxiv

Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acous…

Reinforcement LearningDecision Making

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling

2026-02-19 · Payel Bhattacharjee, Osvaldo Simeone, Ravi Tandon arxiv

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collec…

Data Augmentation

HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding

2026-05-19 · Mengqi Shi, Haopeng Zhang arxiv

While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization…