arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
By Mingzhuo Li, Guang Li, Linfeng Ye, Jiafeng Mao, Takahiro Ogawa, Konstantinos N. Plataniotis, Miki Haseyama
arXiv:2602.05391v3 Announce Type: replace
Abstract: Dataset distillation seeks to synthesize a compact surrogate dataset that enables performance comparable to training on the original dataset for do...
By Qianxin Xia, Jiawei Du, Yuhan Zhang, Xin Zhang, Xuewan He, Wenbo Jiang, Jielei Wang, Tao Luo, Guoming Lu
arXiv:2603. 15553v2 Announce Type: replace-cross Abstract: The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.
By Scott C. Lowe, Anthony Fuller, Sageev Oore, Evan Shelhamer, Graham W. Taylor
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.
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.
By Brun\'o B. Englert, Gijs Dubbelman
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.
By Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Shahab Bakhtiari, Eilif B. Muller, Laurent Charlin