As it is empirically observed that Vision Transformers (ViTs) are quite
...
The crux of label-efficient semantic segmentation is to produce high-qua...
Semantic segmentation usually suffers from a long-tail data distribution...
Domain adaptive semantic segmentation aims to transfer knowledge from a
...
Click-based interactive segmentation enables productive pixel-level
anno...
Masked image modeling (MIM) has attracted much research attention due to...
Video Instance Segmentation(VIS) aims at segmenting and categorizing obj...
There is no settled universal 3D representation for geometry with many
a...
A diffusion model learns to predict a vector field of gradients. We prop...
Self-training has shown great potential in semi-supervised learning. Its...
Person re-identification aims to retrieve persons in highly varying sett...
The crux of semi-supervised semantic segmentation is to assign adequate
...
Non-maximum suppression (NMS) is widely used in object detection pipelin...
This paper aims to address few-shot semantic segmentation. While existin...
In this work we present SwiftNet for real-time semi-supervised video obj...
The core of our approach, Pixel Consensus Voting, is a framework for ins...
We introduce DIODE, a dataset that contains thousands of diverse high
re...