Instance-wise Feature Grouping
In many learning problems, the domain scientist is often interested in discovering the groups of features that are redundant and are important for classification. Moreover, the features that belong to each group, and the important feature groups may vary per sample. But what do we mean by feature redundancy? In this paper, we formally define two types of redundancies using information theory: \textit{Representation} and \textit{Relevant redundancies}. We leverage these redundancies to design a formulation for instance-wise feature group discovery and reveal a theoretical guideline to help discover the appropriate number of groups. We approximate mutual information via a variational lower bound and learn the feature group and selector indicators with Gumbel-Softmax in optimizing our formulation. Experiments on synthetic data validate our theoretical claims. Experiments on MNIST, Fashion MNIST, and gene expression datasets show that our method discovers feature groups with high classification accuracies.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
Instance segmentation in 3D scenes is fundamental in many applications of scene understanding. It is yet challenging due to the compound factors of data irregularity and uncertainty in the numbers of instances. State-of-…
3D Instance SegmentationInstance SegmentationScene UnderstandingSemantic SegmentationOpen-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely on explicit class semantics obtained from l…
DiversityInstance SegmentationOpen-World Instance SegmentationSemantic SegmentationSelf-Supervised Visual Representation Learning from Hierarchical Grouping
We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by mer…
Representation LearningAssociative Embedding: End-to-End Learning for Joint Detection and Grouping
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-p…
2D Human Pose EstimationInstance SegmentationKeypoint DetectionMulti-Person Pose Estimation+2Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be hig…
Contrastive LearningSemi-Supervised Image ClassificationTransfer LearningUnsupervised Image Classification