paper-with-me

Papers

Multi-Modal Hybrid Learning and Sequential Training for RGB-T Saliency Detection

2023-09-13 · Guangyu Ren, Jitesh Joshi, Youngjun Cho

RGB-T saliency detection has emerged as an important computer vision task, identifying conspicuous objects in challenging scenes such as dark environments. However, existing methods neglect the characteristics of cross-modal features and rely solely on network structures to fuse RGB and thermal features. To address this, we first propose a Multi-Modal Hybrid loss (MMHL) that comprises supervised and self-supervised loss functions. The supervised loss component of MMHL distinctly utilizes semantic features from different modalities, while the self-supervised loss component reduces the distance between RGB and thermal features. We further consider both spatial and channel information during feature fusion and propose the Hybrid Fusion Module to effectively fuse RGB and thermal features. Lastly, instead of jointly training the network with cross-modal features, we implement a sequential training strategy which performs training only on RGB images in the first stage and then learns cross-modal features in the second stage. This training strategy improves saliency detection performance without computational overhead. Results from performance evaluation and ablation studies demonstrate the superior performance achieved by the proposed method compared with the existing state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2309.07297

Code (0)

등록된 구현이 없습니다.

Tasks

Saliency Detection

Similar Papers 제목 키워드 기반

Saliency-based Sequential Image Attention with Multiset Prediction

2017-11-14 · NeurIPS 2017 12 · Sean Welleck, Jialin Mao, Kyunghyun Cho, Zheng Zhang

Humans process visual scenes selectively and sequentially using attention. Central to models of human visual attention is the saliency map. We propose a hierarchical visual architecture that operates on a saliency map an…

ClassificationGeneral Classificationimage-classificationImage Classification+5

HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection

2025-09-23 · Ruichao Hou, Xingyuan Li, Tongwei Ren, Dongming Zhou 외 arxiv

RGB-thermal salient object detection (RGB-T SOD) aims to identify prominent objects by integrating complementary information from RGB and thermal modalities. However, learning the precise boundaries and complete objects …

Zero-shot GeneralizationSalient Object DetectionObject LocalizationPrompt Engineering

Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning

2018-11-27 · Xiao Wang, Tao Sun, Rui Yang, Chenglong Li 외

Incorporating various modes of information into the machine learning procedure is becoming a new trend. And data from various source can provide more information than single one no matter they are heterogeneous or homoge…

Decision MakingDecoderDeep Reinforcement Learningobject-detection+7

Instance-aware Image and Sentence Matching with Selective Multimodal LSTM

2016-11-17 · CVPR 2017 7 · Yan Huang, Wei Wang, Liang Wang

Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local sim…

Semantic SimilaritySemantic Textual SimilaritySentence

One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images

2021-07-11 · Weina Jin, Xiaoxiao Li, Ghassan Hamarneh

Being able to explain the prediction to clinical end-users is a necessity to leverage the power of AI models for clinical decision support. For medical images, saliency maps are the most common form of explanation. The m…

AllFeature Importance