AnyUp：通用特徵上採樣

摘要

我們提出了AnyUp，這是一種特徵上採樣方法，可應用於任何解析度的視覺特徵，無需針對特定編碼器進行訓練。現有的基於學習的特徵上採樣器（如DINO或CLIP）需要為每個特徵提取器重新訓練，因此在推理時無法泛化到不同的特徵類型。在本研究中，我們提出了一種推理時特徵無關的上採樣架構，以緩解這一限制並提升上採樣質量。在實驗中，AnyUp為上採樣特徵設定了新的技術標準，能夠泛化到不同的特徵類型，並在保持特徵語義的同時，高效且易於應用於廣泛的下游任務。

English

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.

AnyUp：通用特徵上採樣

AnyUp: Universal Feature Upsampling

摘要

Support