The remarkable performance of the Transformer architecture in natural language processing
has recently also triggered broad interest in Computer Vision. Among other merits …

Graph representation learning aims to effectively encode high-dimensional sparse graph-
structured data into low-dimensional dense vectors, which is a fundamental task that has …

The crux of semi-supervised semantic segmentation is to assign pseudo-labels to the pixels
of unlabeled images. A common practice is to select the highly confident predictions as the …

Large Language Models (LLMs) have achieved excellent performances in various tasks.
However, fine-tuning an LLM requires extensive supervision. Human, on the other hand …

Abstract Contrastive Language-Image Pre-training (CLIP) has made a remarkable
breakthrough in open-vocabulary zero-shot image recognition. Many recent studies …

In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch
from semi-supervised classification, where the prediction of a weakly perturbed image …

Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a wo-stage
scheme. The general idea is to first generate class-agnostic region proposals and then feed …

Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage
unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) …

Consistency learning using input image, feature, or network perturbations has shown
remarkable results in semi-supervised semantic segmentation, but this approach can be …

One-to-one label assignment in object detection has successfully obviated the need of non-
maximum suppression (NMS) as a postprocessing and makes the pipeline end-to-end …