ECKPN: Explicit Class Knowledge Propagation Network for Transductive
Few-shot Learning
- URL: http://arxiv.org/abs/2106.08523v1
- Date: Wed, 16 Jun 2021 02:29:43 GMT
- Title: ECKPN: Explicit Class Knowledge Propagation Network for Transductive
Few-shot Learning
- Authors: Chaofan Chen, Xiaoshan Yang, Changsheng Xu, Xuhui Huang, Zhe Ma
- Abstract summary: Class-level knowledge can be easily learned by humans from just a handful of samples.
We propose an Explicit Class Knowledge Propagation Network (ECKPN) to address this problem.
We conduct extensive experiments on four few-shot classification benchmarks, and the experimental results show that the proposed ECKPN significantly outperforms the state-of-the-art methods.
- Score: 53.09923823663554
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, the transductive graph-based methods have achieved great success in
the few-shot classification task. However, most existing methods ignore
exploring the class-level knowledge that can be easily learned by humans from
just a handful of samples. In this paper, we propose an Explicit Class
Knowledge Propagation Network (ECKPN), which is composed of the comparison,
squeeze and calibration modules, to address this problem. Specifically, we
first employ the comparison module to explore the pairwise sample relations to
learn rich sample representations in the instance-level graph. Then, we squeeze
the instance-level graph to generate the class-level graph, which can help
obtain the class-level visual knowledge and facilitate modeling the relations
of different classes. Next, the calibration module is adopted to characterize
the relations of the classes explicitly to obtain the more discriminative
class-level knowledge representations. Finally, we combine the class-level
knowledge with the instance-level sample representations to guide the inference
of the query samples. We conduct extensive experiments on four few-shot
classification benchmarks, and the experimental results show that the proposed
ECKPN significantly outperforms the state-of-the-art methods.
Related papers
- Accurate Explanation Model for Image Classifiers using Class Association Embedding [5.378105759529487]
We propose a generative explanation model that combines the advantages of global and local knowledge.
Class association embedding (CAE) encodes each sample into a pair of separated class-associated and individual codes.
Building-block coherency feature extraction algorithm is proposed that efficiently separates class-associated features from individual ones.
arXiv Detail & Related papers (2024-06-12T07:41:00Z) - Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral
Image Classification [8.78907921615878]
Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domains.
This paper proposes to learn sample relations on different levels and take them into the model learning process.
arXiv Detail & Related papers (2023-11-02T13:06:03Z) - KGBoost: A Classification-based Knowledge Base Completion Method with
Negative Sampling [29.14178162494542]
KGBoost is a new method to train a powerful classifier for missing link prediction.
We conduct experiments on multiple benchmark datasets, and demonstrate that KGBoost outperforms state-of-the-art methods across most datasets.
As compared with models trained by end-to-end optimization, KGBoost works well under the low-dimensional setting so as to allow a smaller model size.
arXiv Detail & Related papers (2021-12-17T06:19:37Z) - Open-Set Representation Learning through Combinatorial Embedding [62.05670732352456]
We are interested in identifying novel concepts in a dataset through representation learning based on the examples in both labeled and unlabeled classes.
We propose a learning approach, which naturally clusters examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces.
The proposed algorithm discovers novel concepts via a joint optimization of enhancing the discrimitiveness of unseen classes as well as learning the representations of known classes generalizable to novel ones.
arXiv Detail & Related papers (2021-06-29T11:51:57Z) - Neighborhood Contrastive Learning for Novel Class Discovery [79.14767688903028]
We build a new framework, named Neighborhood Contrastive Learning, to learn discriminative representations that are important to clustering performance.
We experimentally demonstrate that these two ingredients significantly contribute to clustering performance and lead our model to outperform state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2021-06-20T17:34:55Z) - Semi-supervised Active Learning for Instance Segmentation via Scoring
Predictions [25.408505612498423]
We propose a novel and principled semi-supervised active learning framework for instance segmentation.
Specifically, we present an uncertainty sampling strategy named Triplet Scoring Predictions (TSP) to explicitly incorporate samples ranking clues from classes, bounding boxes and masks.
Results on medical images datasets demonstrate that the proposed method results in the embodiment of knowledge from available data in a meaningful way.
arXiv Detail & Related papers (2020-12-09T02:36:52Z) - PK-GCN: Prior Knowledge Assisted Image Classification using Graph
Convolution Networks [3.4129083593356433]
Similarity between classes can influence the performance of classification.
We propose a method that incorporates class similarity knowledge into convolutional neural networks models.
Experimental results show that our model can improve classification accuracy, especially when the amount of available data is small.
arXiv Detail & Related papers (2020-09-24T18:31:35Z) - Region Comparison Network for Interpretable Few-shot Image
Classification [97.97902360117368]
Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes.
We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works.
We also present a new way to generalize the interpretability from the level of tasks to categories.
arXiv Detail & Related papers (2020-09-08T07:29:05Z) - Few-shot Classification via Adaptive Attention [93.06105498633492]
We propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples.
As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.
arXiv Detail & Related papers (2020-08-06T05:52:59Z) - UniT: Unified Knowledge Transfer for Any-shot Object Detection and
Segmentation [52.487469544343305]
Methods for object detection and segmentation rely on large scale instance-level annotations for training.
We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
arXiv Detail & Related papers (2020-06-12T22:45:47Z)
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.