Papers › Multi-level Second-order Few-shot Learning

Multi-level Second-order Few-shot Learning

15 Jan 2022arXiv:2201.05916archive 2025-07-28

Hongguang Zhang, Hongdong Li, Piotr Koniusz

We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or unsupervised few-shot image classification and few-shot action recognition. We leverage so-called power-normalized second-order base learner streams combined with features that express multiple levels of visual abstraction, and we use self-supervised discriminating mechanisms. As Second-order Pooling (SoP) is popular in image recognition, we employ its basic element-wise variant in our pipeline. The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning. As SoP can handle convolutional feature maps of varying spatial sizes, we also introduce image inputs at multiple spatial scales into MlSo. To exploit the discriminative information from multi-level and multi-scale features, we develop a Feature Matching (FM) module that reweights their respective branches. We also introduce a self-supervised step, which is a discriminator of the spatial level and the scale of abstraction. Our pipeline is trained in an end-to-end manner. With a simple architecture, we demonstrate respectable results on standard datasets such as Omniglot, mini-ImageNet, tiered-ImageNet, Open MIC, fine-grained datasets such as CUB Birds, Stanford Dogs and Cars, and action recognition datasets such as HMDB51, UCF101, and mini-MIT.

PaperPDFCode

Code

hongguangzhang/mlso-tmm-master officialmentioned in paper 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

Action RecognitionFew Shot Action RecognitionFew-Shot Image ClassificationFew-Shot LearningFew-Shot action recognitionImage ClassificationUnsupervised Few-Shot Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) U-MlSo+PN Accuracy 41.09 #22 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) U-MlSo+PN Accuracy 55.38 #24 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) U-MlSo Accuracy 43.01 #11 of 12 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) U-MlSo Accuracy 57.53 #11 of 12 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

BASE

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