paper-with-me

Papers

CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection

2024-07-09 · Shuang Hao, Chunlin Zhong, He Tang

The depth/thermal information is beneficial for detecting salient object with conventional RGB images. However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied. To tackle this problem, we introduce \textbf{Co}nditional Dropout and \textbf{LA}nguage-driven(\textbf{CoLA}) framework comprising two core components. 1) Language-driven Quality Assessment (LQA): Leveraging a pretrained vision-language model with a prompt learner, the LQA recalibrates image contributions without requiring additional quality annotations. This approach effectively mitigates the impact of noisy inputs. 2) Conditional Dropout (CD): A learning method to strengthen the model's adaptability in scenarios with missing modalities, while preserving its performance under complete modalities. The CD serves as a plug-in training scheme that treats modality-missing as conditions, strengthening the overall robustness of various dual-modal SOD models. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art dual-modal SOD models, under both modality-complete and modality-missing conditions. We will release source code upon acceptance.

📄 PDF Abstract BibTeX arXiv:2407.06780

Code (1)

ssecv/CoLA 공식 구현 pytorch

Tasks

CoLALanguage ModelingLanguage Modellingobject-detectionObject DetectionRGB-D Salient Object DetectionRGB Salient Object DetectionRGB-T Salient Object DetectionSalient Object Detection

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Dropout Neural Network Training Viewed from a Percolation Perspective

2025-12-15 · Finley Devlin, Jaron Sanders arxiv

In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout. Dropout methods are regularisation techniques for training NNs, first introduced by G. Hinton et a…

Aggregating Conformal Prediction Sets via α-Allocation

2025-11-15 · Congbin Xu, Yue Yu, Haojie Ren, Zhaojun Wang 외 arxiv

Conformal prediction offers a distribution-free framework for constructing prediction sets with finite-sample coverage. Yet, efficiently leveraging multiple conformity scores to reduce prediction set size remains a major…

ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration

2024-10-03 · Zixiang Wang, Yinghao Zhu, Huiya Zhao, Xiaochen Zheng 외

We introduce ColaCare, a framework that enhances Electronic Health Record (EHR) modeling through multi-agent collaboration driven by Large Language Models (LLMs). Our approach seamlessly integrates domain-specific expert…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+3

CoLAKE: Contextualized Language and Knowledge Embedding

2020-10-01 · COLING 2020 8 · Tianxiang Sun, Yunfan Shao, Xipeng Qiu, Qipeng Guo 외

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the per…

Entity EmbeddingsKnowledge Graph CompletionKnowledge Probing

COLA: Context-aware Language-driven Test-time Adaptation

2025-09-22 · Aiming Zhang, Tianyuan Yu, Liang Bai, Jun Tang 외 arxiv

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired so…

Test-time Adaptation