Papers › PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image...

PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans

25 Aug 2023arXiv:2308.13651archive 2025-07-28

Giang, Nguyen, Valerie Chen, Mohammad Reza Taesiri, Anh Totti Nguyen

Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing users our probable-class nearest neighbors (PCNN) reduces over-reliance on AI, thus improving their decision accuracy over prior work which only shows only the most-probable (top-1) class examples.

PaperPDFCode

Code

anguyen8/nearest-neighbor-XAI officialmentioned in papermentioned on GitHubpytorch report
giangnguyen2412/PCNN-src-code-TMRL2024 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

Explainable Artificial Intelligence (XAI)Fine-Grained Image ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 ResNet-50 Accuracy 88.59% #6 of 12 Archive leaderboard report
Fine-Grained Image Classification CUB-200-2011 ResNet-50 Accuracy 88.59 #20 of 30 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars ResNet-50 Accuracy 91.06% #76 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Dogs ResNet-50 Accuracy 86.31% #22 of 24 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

Introduced by this paper: PCNN Ranking

PCNN Rankingk-NN

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