arXiv:2601. 21683v2 Announce Type: replace Abstract: While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised learning (local-SSL) have struggled to build functional representations in deep neural networks.
arXiv:2506.11030v2 Announce Type: replace-cross Abstract: Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, s...
arXiv:2610.00753v1 Announce Type: cross Abstract: End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers...
arXiv:2606. 09928v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a biologically inspired alternative to backpropagation by replacing gradient-based credit assignment with local, forward-only objectives.
arXiv:2607. 02447v1 Announce Type: new Abstract: Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data.
The study evaluates self‑supervised learning (SSL) models pretrained on ImageNet‑1k and the Human Protein Atlas (HPA) Field‑of‑View (FOV) for protein localization in microscopy images. DINO‑based Vision Transformer backbones pretrained on either dataset transfer well to the OpenCell dataset, achieving strong performance even without fine‑tuning and improving further when fine‑tuned (0.704 ± 0.027 macro F1 on 17 classes). At the single‑cell level, the HPA‑pretrained model outperforms others in k‑nearest‑neighbor classification across all neighborhood sizes (macro F1 ≥ 0.515).
The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.
Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility. Most existing methods target randomly initialized networks, whereas modern vision systems often adapt frozen pretrained encoders with lightweight modules.
arXiv:2605.19462v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) assumes that solving pretext tasks on unlabeled data yields representations that transfer effectively across d...
arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
arXiv:2506.07188v2 Announce Type: replace Abstract: End-to-end neural networks have become a dominant paradigm in autonomous driving, where reliable deployment requires controllable post-training ada...
arXiv:2606. 03927v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks through purely local, layer-wise optimization.
AdaDim introduces a training strategy for self‑supervised learning that adaptively balances dimensionality increase and mutual information reduction. By gradually regularizing the projection head while encouraging feature decorrelation and sample uniformity, AdaDim achieves up to 3% performance gains over standard SSL baselines without relying on costly techniques such as queues or predictor networks. The method demonstrates that optimal SSL models do not simply maximize dimensionality or minimize mutual information, but find a trade‑off between the two.