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.
arXiv:2610.20158v1 Announce Type: new Abstract: Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regulariz...
Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regularization aims to shape the overall representation di...
arXiv:2610.09700v1 Announce Type: new Abstract: Synthetic hard negatives generated in the representation space have proven effective for unimodal self-supervised learning, but transferring this idea...
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.
arXiv:2603. 15263v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features.
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.
ViTAMINS is a method that incorporates synthetic hard negatives into unsupervised vision transformer pretraining to enhance representation quality. The approach is evaluated on ImageNet and a range of downstream tasks—including transfer learning, image retrieval, copy detection, and image/video segmentation—showing significant performance gains. The synthetic negatives also lead to emergent properties, such as representations that encode explicit semantic information and act as strong classifiers, improving over baselines by up to 11.3%.
arXiv:2610.17440v1 Announce Type: cross Abstract: Dual-encoder vision-language models systematically fail at negation, scoring ''a cat without a dog'' nearly identically to ''a cat with a dog.'' We s...
arXiv:2607. 14995v1 Announce Type: new Abstract: Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare.
arXiv:2606. 18852v1 Announce Type: cross Abstract: Classifying implicit hate speech remains a challenge, as intent is often masked through insinuation and context rather than explicit slurs.
arXiv:2603. 26261v2 Announce Type: replace Abstract: Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples.
arXiv:2605.31349v2 Announce Type: replace-cross Abstract: Hateful meme detection remains a formidable challenge for vision-language models, as existing benchmarks are structurally observational - con...