Combined Scaling for Open-Vocabulary Image Classiﬁcation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Visual Instruction Tuning (2023, background): “…foundation vision models [27, 16], with strong capabilities in open-world visual understanding such as classification [40, 21, 57, 54, 39], detection [29, 62, 33], segmentation [25, 63, 58] and captioning [50, 28], as well as visual generation and editing [42, 43, 56, 15, 44, 30].”
What does a platypus look like? Generating customized prompts for zero-shot image classification (2022, methodology): “Open-vocabulary models [40, 23, 42, 63] achieve high classiﬁcation accuracy across a large number of datasets without labeled training data for those tasks.”
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale (2022, background): “However, the most competitive billionsized vision pre-trained models [31, 61, 67, 116] still heavily rely on supervised or weakly-supervised training with hundreds of millions of (often publicly inaccessible) labeled data.”
Learning Customized Visual Models with Retrieval-Augmented Knowledge (2023, background): “There are an increasing number of studies to improve their generality from various modeling perspectives, including training objectives [11,13,14,38,65,68], scaling techniques [9,40,65], data efficiency [25, 28], and leveraging multilingual correlations [9, 19].”