Abstract We present the Recognize Anything Model (RAM): a strong foundation model for
image tagging. RAM makes a substantial step for foundation models in computer vision …

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which
introduces image tagging into vision-language models to guide the learning of visual …

Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive
to explore the image-to-label correspondence in the vision-language model, ie, CLIP, to …

Many real-world image recognition problems, such as diagnostic medical imaging exams,
are “long-tailed”–there are a few common findings followed by many more relatively rare …

In real medical data, training samples typically show long-tailed distributions with multiple
labels. Class distribution of the medical data has a long-tailed shape, in which the incidence …

Conventional multi-label classification (MLC) methods assume that all samples are fully
labeled and identically distributed. Unfortunately, this assumption is unrealistic in large …

Multi-label image classification is more applicable'in the wild'than single-label classification,
as natural images usually contain multiple objects. However, exhaustively annotating …

Partially annotated images are easy to obtain in multi-label classification. However,
unknown labels in partially annotated images exacerbate the positive-negative imbalance …

Background Since the 2016 WHO guidelines, glioma diagnosis has entered an era of
integrated diagnosis, combining tissue pathology and molecular pathology. The WHO has …

Collecting full annotations to construct multi-label datasets is difficult and labor-consuming.
As an effective solution to relieve the annotation burden, single positive multi-label learning …