paper-with-me

홈 › Papers

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

2023-01-08 · Bin Tang, Zhengyi Liu, Yacheng Tan, Qian He

The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output's fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intra-feature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field SOD.https://github.com/liuzywen/HRTransNet

📄 PDF Abstract BibTeX arXiv:2301.03036

Code (1)

liuzywen/hrtransnet 공식 구현 pytorch

Tasks

global-optimizationObjectobject-detectionObject DetectionSalient Object DetectionVocal Bursts Valence Prediction

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

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…

CoLALanguage ModelingLanguage Modellingobject-detection+5

SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection

2022-04-12 · Zhengyi Liu, Yacheng Tan, Qian He, Yun Xiao

Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features. By absorbing the advantage of trans…

Decoderobject-detectionObject DetectionRGB-T Salient Object Detection+1

HRFormer: High-Resolution Transformer for Dense Prediction

2021-10-18 · Yuhui Yuan, Rao Fu, Lang Huang, WeiHong Lin 외

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and …

Image ClassificationMulti-Person Pose EstimationPose EstimationPrediction+2

HRFormer: High-Resolution Vision Transformer for Dense Predict

2021-12-01 · NeurIPS 2021 12 · Yuhui Yuan, Rao Fu, Lang Huang, WeiHong Lin 외

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and …

Pose EstimationSemantic SegmentationVocal Bursts Intensity Prediction

DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes

2023-03-13 · Sixiang Chen, Tian Ye, Jun Shi, Yun Liu 외

Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges. Recent learning-based depth estimation methods are mainly targeted at dehazing first and estimating depth subsequently from h…

Contrastive LearningDepth Estimation