Papers › Region Comparison Network for Interpretable Few-shot Image Classification

Region Comparison Network for Interpretable Few-shot Image Classification

8 Sep 2020arXiv:2009.03558archive 2025-07-28

Zhiyu Xue, Lixin Duan, Wen Li, Lin Chen, Jiebo Luo

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming. Few-shot image classification has thus been proposed to effectively use only a limited number of labeled examples to train models for new classes. Recent works based on transferable metric learning methods have achieved promising classification performance through learning the similarity between the features of samples from the query and support sets. However, rare of them explicitly considers the model interpretability, which can actually be revealed during the training phase. For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets. Moreover, we also present a visualization strategy named Region Activation Mapping (RAM) to intuitively explain what our method has learned by visualizing intermediate variables in our network. We also present a new way to generalize the interpretability from the level of tasks to categories, which can also be viewed as a method to find the prototypical parts for supporting the final decision of our RCN. Extensive experiments on four benchmark datasets clearly show the effectiveness of our method over existing baselines.

PaperPDFCode

Code

chrisyxue/RCN_for_Interpretable_few_shot officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral ClassificationImage ClassificationMetric Learningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) RCN - ResNet12 Accuracy 69.02 #35 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) RCN - Conv4-64 Accuracy 61.61 #38 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) RCN - ResNet12 Accuracy 82.96 #35 of 39 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) RCN - Conv4-64 Accuracy 77.63 #38 of 39 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) RCN - ResNet12 Accuracy 57.40 #79 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) RCN - Conv4-64 Accuracy 53.57 #88 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) RCN - ResNet12 Accuracy 75.19 #70 of 95 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) RCN - Conv4-64 Accuracy 71.63 #78 of 95 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Interpretability

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections