ArticleAdvances in neural information processing systems2021
Can contrastive learning avoid shortcut solutions?
Article in Advances in neural information processing systems, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 13 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
13 citing papers in PubMed.
- USP-ddG: a unified structural paradigm with data efficacy and mixture-of-experts for predicting mutational effects on protein-protein interactions.Bioinformatics (Oxford, England) · 2026Article
- A Systematic Review of Contrastive Learning in Medical AI: Foundations, Biomedical Modalities, and Future Directions.Bioengineering (Basel, Switzerland) · 2026Review
- Article
- Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification.Sensors (Basel, Switzerland) · 2025Article
- Self-supervised and few-shot learning for robust bioaerosol monitoring.Aerobiologia · 2025Article
- AI analysis of super-resolution microscopy: Biological discovery in the absence of ground truth.The Journal of cell biology · 2024Review
- Article
- DrasCLR: A self-supervised framework of learning disease-related and anatomy-specific representation for 3D lung CT images.Medical image analysis · 2024Article
- Challenges of AI driven diagnosis of chest X-rays transmitted through smart phones: a case study in COVID-19.Scientific reports · 2023Article
- ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast.Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention · 2023Article
- Generalization of vision pre-trained models for histopathology.Scientific reports · 2023Article
- Finding the semantic similarity in single-particle diffraction images using self-supervised contrastive projection learning.npj computational materials · 2023Article
- Reverse translation of artificial intelligence in glaucoma: Connecting basic science with clinical applications.Frontiers in ophthalmology · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
Abstract
The generalization of representations learned via contrastive learning depends crucially on what features of the data are extracted. However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i.e., by inadvertently suppressing important predictive features. We find that feature extraction is influenced by the
Identifiers
35546903PMC9089441What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.