按年被提到
20252026 · 2 次2026
视觉、语音与图像生成›视觉语言与自监督表征·arXiv:2508.10104 · cs.CV

DINOv3

Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza 等 26 人 · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-06-26 · 最近 2026-07-09
2不同的人
2活跃月份
2讨论串
—被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论vatsachak · 2026-06

“JEPA in chess leads to interpretable chess boards: https://arxiv.org/abs/2606.11860 JEPA in image classification leads to interpretable image latents https://arxiv.org/abs/2508.10104 Easy intro to JEPA, demonstrating that interpretability is as easy as running a PCA on latents https://youtu.be/kYkIdXwW2AE?is=CfCBcy1jLt-FfI2E”

Previewing GPT‑5.6 Sol: a next-generation model原评论 ↗
评论typon · 2026-07

“DinoV3 paper: https://arxiv.org/pdf/2508.10104#page=36 "we use a rough estimate of a total 9M GPU hours" From CoreWeave, at current prices (~$2.46/hr spot to ~$6.16/hr on demand) would correspond to $22M–$55M. The dataset is really where the cost is though - they used LVD-1689M - 1.6B images of curated web data from roughly 17B instagram images. This p…”