AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning

Qi Qian, Yuanhong Xu, Juhua Hu

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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
add semantic adversarial augmentation to fixed-feature linear training (average over 11 tasks) (ablation)linear classifier on S+M+B+C features · 11 downstream tasks averageaccuracy (%): 81.1 -> 83.1Improved
increase augmentation step size from 0 to an appropriate value (ablation)SeA · CIFAR-100accuracy (%): 81.1 -> 82.9Improved
random augmentation direction in the batch subspace instead of the semantic adversarial direction (ablation)SeA · CIFAR-100accuracy (%)No clear effect
use raw gradient adversarial direction (Adv) instead of projected semantic direction (ablation)SeA · CIFAR-100accuracy (%)Hurt
feature-space SeA instead of image-space augmentation in linear probing (ablation)single MoCo model · CIFAR-100accuracy (%): 77.8 -> 79.0Improved
concatenate features from four pre-trained models instead of one model (ablation)SeA · 11 downstream tasksaccuracy (%): CIFAR-100 78.5 (C) -> 82.9 (S+M+B+C)Improved
use fixed deep features with SeA instead of fine-tuning (Aircraft, Cars)SeA · Aircraftaccuracy (%): 89.0 -> 67.4Hurt
use fixed deep features with SeA instead of fine-tuning (DTD)SeA · DTDaccuracy (%): 78.6 -> 79.8Improved
use SeA instead of ISDA feature-space augmentationfeature ensemble · 11 tasks averageaccuracy (%): 81.2 -> 83.1Improved
train on fixed features with SeA instead of fine-tuning (cost)SeA · CIFAR-100 running timetime (s): 14,383 -> 40Improved

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