AI Paper Atlas

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

AutoNovel: Automatically Discovering and Learning Novel Visual Categories

Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

TPAMI 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 268 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 BCE loss on pairwise pseudo labels (ablation)AutoNovel · CIFAR-10ACC: 26.2 -> 90.4Improved
add MSE consistency constraint (ablation)AutoNovel · CIFAR-10ACC: 82.6 -> 90.4Improved
add cross-entropy loss on labelled data (ablation)AutoNovel · CIFAR-10ACC: 84.7 -> 90.4Improved
add self-supervised pretraining (ablation)AutoNovel · SVHNACC: 72.9 -> 95.0Improved
add incremental learning schemeAutoNovel · CIFAR-100ACC: 73.2 -> 75.2Improved
use ranking statistics instead of k-means (batch) for pairwise labels (ablation)AutoNovel · CIFAR-10ACC: 42.9 -> 90.4Improved
use ranking statistics instead of nearest neighbor (ablation)AutoNovel · SVHNACC: 78.2 -> 95.0Improved
use cosine similarity instead of ranking statistics (ablation)AutoNovel · CIFAR-10ACC: 90.1 vs 90.4No clear effect
use soft ranking statistics (k=15) instead of hard (ablation)AutoNovel · CIFAR-100ACC: 71.1 vs 73.2No clear effect
replace RotNet with MoCo v2 for self-supervised init (ablation)AutoNovel · CIFAR-100ACC: 73.2 -> 62.5Hurt
use ImageNet pretrained model instead of self-supervisionAutoNovel · SVHNACC: 95.0 -> 40.2Hurt
use ImageNet pretrained model instead of self-supervisionAutoNovel · CIFAR-100ACC: 73.2 -> 87.1Improved

Later papers that compared with this method

1 later accepted paper reports AutoNovel as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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