AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-Supervision Can Be a Good Few-Shot Learner

Yuning Lu, Liangjian Wen, Jianzhuang Liu, Yajing Liu, Xinmei Tian

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-supervised knowledge distillation from ResNet-50 teacher (ablation)UniSiam ResNet-18 · mini-ImageNet 5-way 5-shotaccuracy (%): 79.11 -> 80.35Improved
add self-supervised knowledge distillation from ResNet-50 teacher (ablation)UniSiam ResNet-34 · mini-ImageNet 5-way 5-shotaccuracy (%): 79.69 -> 81.39Improved
add self-supervised knowledge distillation from ResNet-50 teacher (ablation)UniSiam ResNet-10 · mini-ImageNet 5-way 5-shotaccuracy (%): 76.94 -> 78.58Improved
add uniformity regularization (UniSiam) to SimSiam under strong augmentation (ablation)SimSiam ResNet-50 · mini-ImageNet 5-way 5-shotaccuracy (%): 79.66 -> 83.18Improved
switch from default to strong data augmentation (ablation)SimSiam ResNet-50 · mini-ImageNet 5-way 5-shotaccuracy (%): 81.75 -> 79.66Hurt
switch from default to strong data augmentation (ablation)UniSiam ResNet-50 · mini-ImageNet 5-way 5-shotaccuracy (%): 81.93 -> 83.18Improved
use MINE uniformity instead of NCE uniformity (ablation)UniSiam ResNet-18 strong DA · mini-ImageNet 5-way 5-shotaccuracy (%): 80.66 -> 81.13Improved
use asymmetric alignment instead of symmetric alignment (ablation)UniSiam ResNet-18 strong DA · mini-ImageNet 5-way 5-shotaccuracy (%): 80.72 -> 81.13Improved
increase backbone from ResNet-10 to ResNet-50 (ablation)supervised pre-training · mini-ImageNetaccuracy (%): decreased by 0.2%Hurt
increase backbone from ResNet-10 to ResNet-50 (ablation)self-supervised pre-training · mini-ImageNetaccuracy (%): improvement larger than 4%Improved
increase input image size from 160x160 to 384x384 (ablation)self-supervised pre-training · mini-ImageNetaccuracy (%)Improved
add RandAugment to default plus vertical flip augmentation (ablation)SimSiam · mini-ImageNetaccuracy (%)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy