ProLFA: Representative Prototype Selection for Local Feature Aggregation
Given a set of hand-crafted local features, acquiring a global representation via aggregation is a promising technique to boost computational efficiency and improve task performance. Existing feature aggregation (FA) approaches, including Bag of Words and Fisher Vectors, usually fail to capture the desired information due to their pipeline mode. In this paper, we propose a generic formulation to provide a systematical solution (named ProLFA) to aggregate local descriptors. It is capable of producing compact yet interpretable representations by selecting representative prototypes from numerous descriptors, under relaxed exclusivity constraint. Meanwhile, to strengthen the discriminability of the aggregated representation, we rationally enforce the domain-invariant projection of bundled descriptors along a task-specific direction. Furthermore, ProLFA is also provided with a powerful generalization ability to deal flexibly with the semi-supervised and fully supervised scenarios in local feature aggregation. Experimental results on various descriptors and tasks demonstrate that the proposed ProLFA is considerably superior over currently available alternatives about feature aggregation.
Code (1)
Tasks
Computational EfficiencyPrototype SelectionSimilar Papers 제목 키워드 기반
Modelling Multi-modal Cross-interaction for ML-FSIC Based on Local Feature Selection
The aim of multi-label few-shot image classification (ML-FSIC) is to assign semantic labels to images, in settings where only a small number of training examples are available for each label. A key feature of the multi-l…
feature selectionFew-Shot Image Classificationimage-classificationImage Classification+1Interpretable Multiple-Kernel Prototype Learning for Discriminative Representation and Feature Selection
Prototype-based methods are of the particular interest for domain specialists and practitioners as they summarize a dataset by a small set of representatives. Therefore, in a classification setting, interpretability of t…
feature selectionContinual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection
We introduce a novel framework for Continual Learning in 3D object classification (CL3D). Our approach is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as poi…
3D Object ClassificationClusteringContinual LearningBalanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data
Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced…
Cluster Representatives Selection in Non-Metric Spaces for Nearest Prototype Classification
The nearest prototype classification is a less computationally intensive replacement for the $k$-NN method, especially when large datasets are considered. In metric spaces, centroids are often used as prototypes to repre…