</> Code with Papers by Syntology

Papers › Match Them Up: Visually Explainable Few-shot Image Classification

Match Them Up: Visually Explainable Few-shot Image Classification

25 Nov 2020arXiv:2011.12527archive 2025-07-28

Bowen Wang, Liangzhi Li, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara

Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to novel (unseen) categories. However, there is no guarantee, especially for the latter part. This issue leads to the unknown nature of the inference process in most FSL methods, which hampers its application in some risk-sensitive areas. In this paper, we reveal a new way to perform FSL for image classification, using visual representations from the backbone model and weights generated by a newly-emerged explainable classifier. The weighted representations only include a minimum number of distinguishable features and the visualized weights can serve as an informative hint for the FSL process. Finally, a discriminator will compare the representations of each pair of the images in the support set and the query set. Pairs with the highest scores will decide the classification results. Experimental results prove that the proposed method can achieve both good accuracy and satisfactory explainability on three mainstream datasets.

PaperPDFCode

Code

wbw520/MTUNet officialmentioned in papermentioned 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 Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) MTUNet+WRN Accuracy 68.34 #36 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) MTUNet+ResNet-18 Accuracy 66.31 #37 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) MTUNet+WRN Accuracy 82.93 #36 of 39 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) MTUNet+ResNet-18 Accuracy 80.16 #37 of 39 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MTUNet+WRN Accuracy 56.12 #82 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MTUNet+ResNet-18 Accuracy 55.03 #85 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MTUNet+WRN Accuracy 71.93 #77 of 95 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MTUNet+ResNet-18 Accuracy 70.22 #84 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) MTUNet+WRN Accuracy 62.42 #46 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) MTUNet+ResNet-18 Accuracy 61.27 #47 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) MTUNet+WRN Accuracy 80.05 #44 of 51 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) MTUNet+ResNet-18 Accuracy 77.82 #47 of 51 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.

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