AI Paper Atlas

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

Mutual exclusivity as a challenge for deep neural networks

Kanishk Gandhi, Brenden M Lake

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 9 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
Train feedforward networks with maximum-likelihood loss on one-to-one synthetic mappingsFeedforward classifiers · Synthetic classificationME scoreHurt
Use entropy regularization instead of the standard setup (ablation)Feedforward classifier · Synthetic classificationME scoreNo clear effect
Add entropy regularization (ablation)Feedforward classifier · Synthetic classificationconfidence on seen classesHurt
Train GRU seq2seq models on one-to-one synthetic mappingsSeq2seq models with and without attention · Synthetic sequence mappingME scoreHurt
Add attention to the seq2seq model (ablation)GRU seq2seq model · Synthetic sequence mappingME scoreNo clear effect
Use an oracle signal and add an ME bias of 5 rather than 0 (ablation)CNN classifier · Omniglot online classification, new-class instancesclassification loss: 5 from 0Improved
Increase the oracle ME bias beyond 5 (ablation)CNN classifier · Omniglot online classification, new-class instancesclassification lossNo clear effect
Use standard online classifiers rather than the dataset's new-class occurrence patternOmniglot and ImageNet classifiers · Lifelong image classificationME score: 8,960 vs 111,872Hurt
Assume a new source-language word predicts a new target-language wordLifelong translation learner · IWSLT'14, WMT'14, and WMT'15conditional probability of new target word: 0.9: 0.3K–4K; 0.5: 3K–40K; 0.1: 90K–150KMixed

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