TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning

Li, Haoquan; Zhang, Laoming; Zhang, Daoan; Fu, Lang; Yang, Peng; Zhang, Jianguo

doi:10.1007/978-3-031-20044-1_30

Cited by 4 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of Graph Neural Networks (GNNs) to process graph-structured data has also become common, where concise and elegant learning paradigms like Messagepassing Neural Networks(MPNNs) (Gilmer et al 2017) have achieved great success. Although deep learning has greatly enhanced the influence of artificial intelligence in various fields in recent years (Wang et al 2022Zhang et al 2022;Li et al 2022;. With the indepth researche of GNNs, the foundational problem that limits the expressive power of GNNs is discovered, namely that the paradigm of their message passing limits their ability to perceive structures.…”

Section: Introductionmentioning

confidence: 99%

Substructure Aware Graph Neural Networks

Zeng

Liu

Chen

et al. 2023

AAAI

View full text Add to dashboard Cite

Despite the great achievements of Graph Neural Networks (GNNs) in graph learning, conventional GNNs struggle to break through the upper limit of the expressiveness of first-order Weisfeiler-Leman graph isomorphism test algorithm (1-WL) due to the consistency of the propagation paradigm of GNNs with the 1-WL.Based on the fact that it is easier to distinguish the original graph through subgraphs, we propose a novel framework neural network framework called Substructure Aware Graph Neural Networks (SAGNN) to address these issues. We first propose a Cut subgraph which can be obtained from the original graph by continuously and selectively removing edges. Then we extend the random walk encoding paradigm to the return probability of the rooted node on the subgraph to capture the structural information and use it as a node feature to improve the expressiveness of GNNs. We theoretically prove that our framework is more powerful than 1-WL, and is superior in structure perception. Our extensive experiments demonstrate the effectiveness of our framework, achieving state-of-the-art performance on a variety of well-proven graph tasks, and GNNs equipped with our framework perform flawlessly even in 3-WL failed graphs. Specifically, our framework achieves a maximum performance improvement of 83% compared to the base models and 32% compared to the previous state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Substructure Aware Graph Neural Networks

Zeng

Liu

Chen

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…On the contrary, these windows are intact in our model. natural language (Devlin et al 2019;Brown et al 2020), computer vision (Wang and Chen 2023b;Zhang et al 2022;Li et al 2022;Wang et al 2023), and graph mining (Liu et al 2022a(Liu et al ,b, 2023d. Specifically, the existing approaches can generally be divided into depth-map-based and volumebased.…”

Section: Introductionmentioning

confidence: 99%

Flora: Dual-Frequency LOss-Compensated ReAl-Time Monocular 3D Video Reconstruction

Wang

Gong

Wang

et al. 2023

AAAI

View full text Add to dashboard Cite

In this work, we propose a real-time monocular 3D video reconstruction approach named Flora for reconstructing delicate and complete 3D scenes from RGB video sequences in an end-to-end manner. Specifically, we introduce a novel method with two main contributions. Firstly, the proposed feature aggregation module retains both color and reliability in a dual-frequency form. Secondly, the loss compensation module solves missing structure by correcting losses for falsely pruned voxels. The dual-frequency feature aggregation module enhances reconstruction quality in both precision and recall, and the loss compensation module benefits the recall. Notably, both proposed contributions achieve great results with negligible inferencing overhead. Our state-of-the-art experimental results on real-world datasets demonstrate Flora's leading performance in both effectiveness and efficiency. The code is available at https://github.com/NoOneUST/Flora.

show abstract

Target Oriented Dynamic Adaption for Cross-Domain Few-Shot Learning

Chang,

Du,

Song

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Few-shot learning has achieved satisfactory progress over the years, but these methods implicitly hypothesize that the data in the base (source) classes and novel (target) classes are sampled from the same data distribution (domain), which is often invalid in reality. The purpose of cross-domain few-shot learning (CD-FSL) is to successfully identify novel target classes with a small quantity of labeled instances on the target domain under the circumstance of domain shift between the source domain and the target domain. However, in CD-FSL, the knowledge learned by the network on the source domain often suffers from the situation of inadaptation when it is transferred to the target domain, since the instances on the source and target domains do not obey the same data distribution. To surmount this problem, we propose a Target Oriented Dynamic Adaption (TODA) model, which uses a tiny amount of target data to orient the network to dynamically adjust and adapt during training. Specifically, this work proposes a domain-specific adapter to ameliorate the network inadaptability issues in transfer to the target domain. The domain-specific adapter can make the extracted features more specific to the tasks in the target domain and reduce the impact of tasks in the source domain by combining them with the mainstream backbone network. In addition, we propose an adaptive optimization method in the network optimization process, which assigns different weights according to the importance of different optimization tasks. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our TODA method.

show abstract

TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning

Cited by 4 publications

References 29 publications

Substructure Aware Graph Neural Networks

Substructure Aware Graph Neural Networks

Flora: Dual-Frequency LOss-Compensated ReAl-Time Monocular 3D Video Reconstruction

Target Oriented Dynamic Adaption for Cross-Domain Few-Shot Learning

Contact Info

Product

Resources

About