AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

PatchMix Augmentation to Identify Causal Features in Few-Shot Learning

Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 30 citations (OpenAlex)

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
replace Mixup/CutMix with PatchMix augmentation (ablation)FSL baseline · miniImageNet 5-wayaccuracy (%): CutMix 65.91 -> PatchMix 68.34 (1-shot), 79.10 -> 83.16 (5-shot)Improved
add Manifold Mixup to baseline (ablation)FSL baseline · miniImageNet 5-way 5-shotaccuracy (%): 77.95 vs baseline decrease of 1.39%Hurt
add CutMix to CAN (ablation)CAN · miniImageNet 5-way 5-shotaccuracy (%): 81.42 -> 79.53Hurt
add PatchMix to CAN (ablation)CAN · miniImageNet 5-wayaccuracy (%): 65.05 -> 67.77 (1-shot), 81.42 -> 82.54 (5-shot)Improved
add correlation-guided reconstruction (gumbel-softmax) after PatchMix (ablation)PatchMix · miniImageNet 5-wayaccuracy (%): 68.34 -> 69.38 (1-shot), 83.16 -> 84.14 (5-shot)Improved
add vanilla reconstruction (ablation)PatchMix · miniImageNet 5-wayaccuracy (%): 68.34 -> 68.59No clear effect
use softmax instead of gumbel-softmax in CGR (ablation)CGR · miniImageNet 5-wayaccuracy (%): 69.38 -> 68.81Hurt
add global hardness to PatchMix distillation (ablation)hardness-aware PatchMix · miniImageNet 5-wayaccuracy (%): 68.61 -> 69.38 (1-shot), 83.46 -> 84.14 (5-shot)Improved
use global instead of local hardness (ablation)hardness-aware PatchMix · miniImageNet 5-way 1-shotaccuracy (%): 69.07 -> 69.38Improved
use all mixed images instead of mix plus original (ablation)PatchMix · miniImageNet 5-way 1-shotaccuracy (%): 68.06 -> 68.61Improved
use grid size 11x11 instead of 6x6 (ablation)PatchMix · miniImageNet 5-way 1-shotaccuracy (%): 67.95 -> 68.61Improved
replace DeepCluster with PatchMix in unsupervised FSL (ablation)CACTUs-ProtoNets · miniImageNet unsupervised 1-shotaccuracy (%): 40.69 -> 41.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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