← Back to all news
arXiv AI By Vicente Balmaseda, Bokun Wang, Ching-Long Lin, Tianbao Yang

Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning

Read the original on arXiv AI →

The paper introduces GloFND, an optimization-based method that learns a threshold for each anchor image during training to automatically detect false negative pairs in self-supervised contrastive learning. Unlike prior approaches that only consider false negatives within a mini-batch, GloFND globally identifies them across the entire dataset while keeping per-iteration computation independent of dataset size. Experiments on image and image-text data show the method’s effectiveness, and the implementation is publicly available.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 21

The Impact of Semantic Pairs on Self-Supervised Representation Learning

The paper investigates the effect of using semantic positive pairs—different instances of the same class—in self‑supervised visual representation learning. By creating matched ImageNet‑1K subsets of augmented pairs and manually curated semantic pairs, the authors compare contrastive and non‑contrastive SSL methods under identical training conditions. Across transfer learning and object detection tasks, semantic‑pair pretraining consistently outperforms augmented‑pair pretraining, with contrastive methods like SimCLR showing the largest gains, indicating that semantic pairs foster additional invariances beyond standard augmentations.

By Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
computer-visionfine-tuning
More like this →
arXiv AI
Aug 5

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

arXiv:2508. 00955v3 Announce Type: replace-cross Abstract: Adapting generative Multimodal Large Language Models (MLLMs) into universal embedding models typically demands resource-intensive contrastive pre-training, while traditional hard negative mining methods suffer from severe false negative contamination.

By Yeong-Joon Ju, Seong-Whan Lee
llmsragfine-tuningmultimodalbenchmarks
More like this →