AI Paper Atlas

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

On Learning Latent Models with Multi-Instance Weak Supervision

Kaifu Wang, Efthymia Tsamoura, Dan Roth

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 1 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
use weak supervision (NLog) instead of fully supervised SL with same 4K samplesNLog · WEIGHTED-SUM M=2accuracy: 93 -> 97Improved
add pretraining with 16 directly labeled samples (ablation)Scallop(1) · WEIGHTED-SUM M=3accuracy: 21 -> 97Improved
add pretraining with 16 directly labeled samples (ablation)DLog-A · WEIGHTED-SUM M=2accuracy: 34 -> 80Improved
add pretraining with 16 directly labeled samples (ablation)Scallop(4) · WEIGHTED-SUM M=4accuracy: 51 -> 78Improved
add pretraining with 8 or 16 labeled samples (ablation)SL, DLog, NLog, NASP · WEIGHTED-SUM M=2accuracy: 97 -> 97No clear effect
increase number of digits M from 2 to 4 (no pretraining) (ablation)Scallop(4) · WEIGHTED-SUMaccuracy: 97 -> 51Hurt
use top-k semantic loss with k=4 instead of k=1 (ablation)Scallop · WEIGHTED-SUM M=4, #16accuracy: 54 -> 78Improved
use top-k=4 instead of k=1 without pretraining (ablation)Scallop · WEIGHTED-SUM M=3, #0accuracy: 21 -> 53Improved
use DLog-A approximation instead of exact NLog (ablation)DLog-A · WEIGHTED-SUM M=3, #0accuracy: 61 -> 24Hurt
use NLog top-5 approximation instead of exact semantic loss (ablation)NLog(5) · WEIGHTED-SUM M=3, #0accuracy: 61 -> 27Hurt
use ABL or ENT instead of semantic-loss frameworksABL, ENT · WEIGHTED-SUM M=2accuracy: 97 -> 9Hurt
double SL training data from 4K to 8KSL · WEIGHTED-SUM M=2accuracy: 93 -> 96Improved

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