Dense Prediction with Attentive Feature Aggregation

Yang, Yung-Hsu; Huang, Tsung‐Wei; Bulò, Samuel Rota; Kontschieder, Peter; Yu, Fisher

doi:10.48550/arxiv.2111.00770

Cited by 2 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, the branches are forced to cooperate with each other. Our HFA is also different from the dense link structure in [62], we aim to discover diverse concepts and details for fine-grained recognition, other than dense predictions for scene segmentation.…”

Section: Hierarchical Feature Aggregationmentioning

confidence: 99%

WITHDRAWN: Hierarchical Attentive Feature Aggregation for Person Re-identification

Dong,

2023

Preprint

View full text Add to dashboard Cite

Recent efforts on person re-identification have shown promising results by learning discriminative features via multi-branch network. To further boost feature discrimination, attention mechanism has also been extensively employed. However, the branches in existing models generally work independently, which may compromise the ability of mining diverse features. To mitigate this issue, a novel framework called Hierarchical Attentive Feature Aggregation (Hi-AFA) is proposed. In Hi-AFA, a hierarchical aggregation mechanism is applied to learn attentive features. The current feature map is not only fed into the next stage, but also aggerated into another branch, leading to hierarchical feature flows along depth and parallel branches. We also present a simple feature suppression operation and a lightweight dual attention module with only a few parameters to guide feature learning. By this manner, the branches could cooperate to mine richer and more diverse feature representations. We integrate the hierarchical aggregation and multi-granularity feature learning into a unified architecture that builds upon OSNet, resulting a resource-economical and effective person re-identification model. Extensive experiments on three public datasets, including Market-1501, DukeMTMC-reID, and CUHK03, are conducted to validate the effectiveness of the proposed method, and results show that state-of-the-art performance is achieved.

show abstract

Section: Hierarchical Feature Aggregationmentioning

confidence: 99%

WITHDRAWN: Hierarchical Attentive Feature Aggregation for Person Re-identification

Dong,

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Yang et al [29] gradually combine low-to-high resolution features by interpolation, deconvolution, and a series of convolutions to extract the local and global features involved at all resolutions. Yang et al [35] aggregate the feature maps of different layers using spatial attention and channel attention.…”

Section: A High-resolution Networkmentioning

confidence: 99%

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

Tang

Liu

Tan

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

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 intrafeature 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

show abstract

Dense Prediction with Attentive Feature Aggregation

Cited by 2 publications

References 34 publications

WITHDRAWN: Hierarchical Attentive Feature Aggregation for Person Re-identification

WITHDRAWN: Hierarchical Attentive Feature Aggregation for Person Re-identification

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

Contact Info

Product

Resources

About