arXiv:2602. 02381v2 Announce Type: replace Abstract: Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs.
Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data.
arXiv:2603.20111v2 Announce Type: replace Abstract: The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emph...
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.
The paper reports a controlled study of self‑supervised learning (SSL) objectives for image and video pretraining under limited data, architecture, and compute budgets. It compares contrastive, reconstruction, feature‑prediction, and diffusion methods, finding that DINOv2‑style pretraining delivers the best overall performance. Combining DINOv2 with video SSL objectives such as VideoMAE improves image classification and segmentation but harms video tracking and camera‑pose estimation, highlighting a trade‑off between semantic and geometric learning.
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:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information. Learning disentangled representations is a principled way to identify these underlying shared and unique factors that are hidden in observational data.
arXiv:2606. 05109v1 Announce Type: new Abstract: To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interactions without sacrificing modality-specific information.
arXiv:2603. 15553v2 Announce Type: replace-cross Abstract: The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.
arXiv:2602. 09764v2 Announce Type: replace-cross Abstract: Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions.
arXiv:2607. 16725v1 Announce Type: cross Abstract: Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant.
arXiv:2608. 08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy.