Papers › Revisiting a kNN-based Image Classification System with High-capacity Storage

Revisiting a kNN-based Image Classification System with High-capacity Storage

3 Apr 2022arXiv:2204.01186archive 2025-07-28

Kengo Nakata, Youyang Ng, Daisuke Miyashita, Asuka Maki, Yu-Chieh Lin, Jun Deguchi

In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model parameters. Moreover, users cannot verify the validity of inference results or evaluate the contribution of knowledge to the results. In this paper, we investigate a system that stores knowledge for image classification, such as image feature maps, labels, and original images, not in model parameters but in external high-capacity storage. Our system refers to the storage like a database when classifying input images. To increase knowledge, our system updates the database instead of fine-tuning model parameters, which avoids catastrophic forgetting in incremental learning scenarios. We revisit a kNN (k-Nearest Neighbor) classifier and employ it in our system. By analyzing the neighborhood samples referred by the kNN algorithm, we can interpret how knowledge learned in the past is used for inference results. Our system achieves 79.8% top-1 accuracy on the ImageNet dataset without fine-tuning model parameters after pretraining, and 90.8% accuracy on the Split CIFAR-100 dataset in the task incremental learning setting.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Classification Continual Learning Image Classification Incremental Learning Vocal Bursts Intensity Prediction image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Continual Learning	Cifar100 (20 tasks)	kNN-CLIP	Average Accuracy	90.8	#3 of 9	Archive leaderboard	report
Image Classification	CIFAR-10	kNN-CLIP	Percentage correct	97.3	#88 of 265	Archive leaderboard	report
Image Classification	CIFAR-100	kNN-CLIP	Percentage correct	81.7	#115 of 211	Archive leaderboard	report
Image Classification	ImageNet	kNN-CLIP	Top 1 Accuracy	79.8%	#736 of 1060	Archive leaderboard	report
Image Classification	ImageNet ReaL	kNN-CLIP	Accuracy	84%	#46 of 57	Archive leaderboard	report
Image Classification	STL-10	kNN-CLIP	Percentage correct	99.6	#2 of 117	Archive leaderboard	report
Incremental Learning	ImageNet - 10 steps	kNN-CLIP	Average Incremental Accuracy	85.5	#1 of 10	Archive leaderboard	report
Incremental Learning	ImageNet100 - 10 steps	kNN-CLIP	Average Incremental Accuracy	85.1	#1 of 13	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