Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk
Minimization
- URL: http://arxiv.org/abs/2105.00101v1
- Date: Fri, 30 Apr 2021 21:47:36 GMT
- Title: Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk
Minimization
- Authors: Yubin Ge, Site Li, Xuyang Li, Fangfang Fan, Wanqing Xie, Jane You,
Xiaofeng Liu
- Abstract summary: We propose to incorporate the risk-aware inter-class correlation in a discrete optimal transport (DOT) training framework.
Specifically, we define the tree induced error (TIE) on a hierarchical semantic tree and extend it to its increasing function.
We achieve promising results on several large scale image classification tasks with a semantic tree structure in a plug and play manner.
- Score: 26.929277114533498
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The widely-used cross-entropy (CE) loss-based deep networks achieved
significant progress w.r.t. the classification accuracy. However, the CE loss
can essentially ignore the risk of misclassification which is usually measured
by the distance between the prediction and label in a semantic hierarchical
tree. In this paper, we propose to incorporate the risk-aware inter-class
correlation in a discrete optimal transport (DOT) training framework by
configuring its ground distance matrix. The ground distance matrix can be
pre-defined following a priori of hierarchical semantic risk. Specifically, we
define the tree induced error (TIE) on a hierarchical semantic tree and extend
it to its increasing function from the optimization perspective. The semantic
similarity in each level of a tree is integrated with the information gain. We
achieve promising results on several large scale image classification tasks
with a semantic tree structure in a plug and play manner.
Related papers
- Learning Hierarchical Semantic Classification by Grounding on Consistent Image Segmentations [37.80849457554078]
Hierarchical semantic classification requires the prediction of a taxonomy tree instead of a single flat level of the tree.
We build upon recent work on learning hierarchical segmentation for flat-level recognition.
We introduce a Tree-path KL Divergence loss to enforce consistent accurate predictions across levels.
arXiv Detail & Related papers (2024-06-17T14:56:51Z) - Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training.
It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby.
It can be combined with both discriminative and generative neural models.
arXiv Detail & Related papers (2024-05-12T22:18:25Z) - Benchmarking Individual Tree Mapping with Sub-meter Imagery [6.907098367807166]
We introduce an evaluation framework suited for individual tree mapping in any physical environment.
We review and compare different approaches and deep architectures, and introduce a new method that we experimentally prove to be a good compromise between segmentation and detection.
arXiv Detail & Related papers (2023-11-14T08:21:36Z) - Differentiable Tree Operations Promote Compositional Generalization [106.59434079287661]
Differentiable Tree Machine (DTM) architecture integrates interpreter with external memory and agent that learns to sequentially select tree operations.
DTM achieves 100% while existing baselines such as Transformer, Tree Transformer, LSTM, and Tree2Tree LSTM achieve less than 30%.
arXiv Detail & Related papers (2023-06-01T14:46:34Z) - Social Interpretable Tree for Pedestrian Trajectory Prediction [75.81745697967608]
We propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task.
A path in the tree from the root to leaf represents an individual possible future trajectory.
Despite the hand-crafted tree, the experimental results on ETH-UCY and Stanford Drone datasets demonstrate that our method is capable of matching or exceeding the performance of state-of-the-art methods.
arXiv Detail & Related papers (2022-05-26T12:18:44Z) - Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation [141.16965264264195]
Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained supervisions.
We propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels.
arXiv Detail & Related papers (2022-03-21T05:16:23Z) - Meta Ordinal Regression Forest for Medical Image Classification with
Ordinal Labels [37.121792169424744]
We propose a novel meta ordinal regression forest (MORF) method for medical image classification with ordinal labels.
MORF learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning framework.
Experimental results on two medical image classification datasets with ordinal labels demonstrate the superior performances of our MORF method over existing state-of-the-art methods.
arXiv Detail & Related papers (2022-03-15T08:43:57Z) - TopicNet: Semantic Graph-Guided Topic Discovery [51.71374479354178]
Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner.
We introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning.
arXiv Detail & Related papers (2021-10-27T09:07:14Z) - TopNet: Topology Preserving Metric Learning for Vessel Tree
Reconstruction and Labelling [22.53041565779104]
We propose a novel deep learning architecture for vessel tree reconstruction.
The network architecture simultaneously solves the task of detecting voxels on vascular centerlines (i.e. nodes) and estimates connectivity between center-voxels (edges) in the tree structure to be reconstructed.
A thorough evaluation on public IRCAD dataset shows that the proposed method considerably outperforms existing semantic segmentation based methods.
arXiv Detail & Related papers (2020-09-18T07:55:58Z) - Discretization-Aware Architecture Search [81.35557425784026]
This paper presents discretization-aware architecture search (DAtextsuperscript2S)
The core idea is to push the super-network towards the configuration of desired topology, so that the accuracy loss brought by discretization is largely alleviated.
Experiments on standard image classification benchmarks demonstrate the superiority of our approach.
arXiv Detail & Related papers (2020-07-07T01:18:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.