Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

few-shot-image-classification

Unsupervised Few-Shot Learning

3260 papers • 126 benchmarks • 313 datasets

In contrast to supervised few-shot learning, only the unlabeled dataset is available in the pre-training or meta-training stage for unsupervised few-shot learning.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in few-shot-image-classification

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find few-shot-image-classification models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Self-Supervision Can Be a Good Few-Shot Learner

Xinmei Tian, Jianzhuang Liu, Yuning Lu, Liangjiang Wen, Yajing Liu•Mon Jul 18 2022

This work proposes an effective unsupervised FSL method, learning representations with self-supervision, following the InfoMax principle, which achieves comparable performance on widely used FSL benchmarks without any labels of the base classes.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

Carlos Medina, A. Devos, M. Grossglauser•Thu Jun 18 2020

It is demonstrated that the self-supervised prototypical transfer learning approach ProtoTransfer outperforms state-of-the-art unsupervised meta-learning methods on few-shot tasks from the mini-ImageNet dataset and has comparable performance to supervised methods, but requires orders of magnitude fewer labels.

57 0

Paper Graph

Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning

Philip H. S. Torr, Piotr Koniusz, Hongguang Zhang, Songlei Jian, Hongdong Li•Sat Jan 11 2020

This work rethink the relations between class concepts, and proposes a novel Absolute-relative Learning paradigm to fully take advantage of label information to refine the image an relation representations in both supervised and unsupervised scenarios.

71 0

Paper Graph

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

Wenbin Li, Yinghuan Shi, Yang Gao, Tiexin Qin•Sun Apr 12 2020

This paper develops a novel framework called Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation (ULDA), which pays attention to the distribution diversity inside each constructed pretext few-shot task when using data augmentation.

20 0

Paper Graph

Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks

Han-Jia Ye, De-chuan Zhan, Lu Han•Sun Nov 29 2020

This work removes the requirement of base class labels and learns generalizable embeddings via Unsupervised Meta-Learning (UML), and applies embedding-based classifiers to novel tasks with labeled few-shot examples during meta-test.

37 0

Paper Graph

Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test

S. Lowe, Lu Yihe, P. Lewis, M. C. W. Rossum•Sun Nov 17 2019

It is found that the program synthesis classifier could not solve problems involving shape distances, because it relied on symbolic computation which scales poorly with input dimension and adding distances into such computation would increase the dimension combinatorially with the number of shapes in an image.

5 0

Paper Graph

Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings

Wenbin Li, Yang Gao, Xuesong Yang, Meihao Kong, Jing Huo, Jiebo Luo•Wed Jul 21 2021

It is shown that a simple Triplet-based loss (Trip) can achieve surprisingly good performance without requiring large batches or asymmetry designs and a simple plug-and-play RandOm MApping (ROMA) strategy is proposed by randomly mapping samples into other spaces and requiring these randomly projected samples to satisfy the same relationship indicated by the triplets.

0 0

Paper Graph

Self-Attention Message Passing for Contrastive Few-Shot Learning

Ashutosh Kumar Singh, Ojas Shirekar, H. Jamali-Rad•Tue Oct 11 2022

This work proposes a novel self-attention based message passing contrastive learning approach (coined as SAMP-CLR) for U-FSL pre-training and proposes an optimal transport based fine-tuning strategy (OT) to efficiently induce task awareness into the authors' novel end-to-end unsupervised few-shot classification framework (SAMPTransfer).

6 0

Paper Graph

UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps

J. Lambourne, P. Jayaraman, Peter Meltzer, Hooman Shayani, A. Khasahmadi, Aditya Sanghi•Tue Apr 27 2021

UVStyle-Net is proposed, a style similarity measure for B-Reps that leverages the style signals in the second order statistics of the activations in a pre-trained (unsupervised) 3D encoder, and learns their relative importance to a subjective end-user through few-shot learning.

6 0

Paper Graph

Adding a benchmark result helps the community track progress.

Unsupervised Few-Shot Learning | State-of-the-Art