Deep co-training has been introduced to semi-supervised segmentation and...
We generalize the class vectors found in neural networks to linear subsp...
Out-of-Distribution (OOD) detection is critical for the reliable operati...
As the core building block of vision transformers, attention is a powerf...
Out-of-distribution (OOD) detection is vital to safety-critical machine
...
In this study, we dive deep into the unique challenges in semi-supervise...
In this work, we revisit the weak-to-strong consistency framework,
popul...
Existing research addresses scene graph generation (SGG) – a critical
te...
Most of the existing Out-Of-Distribution (OOD) detection algorithms depe...
Weakly-Supervised Semantic Segmentation (WSSS) segments objects without ...
Current out-of-distribution (OOD) detection benchmarks are commonly buil...
We present MMOCR-an open-source toolbox which provides a comprehensive
p...
Deep semi-supervised learning (SSL) has experienced significant attentio...
Transformers with powerful global relation modeling abilities have been
...
The performance of object detection, to a great extent, depends on the
a...
One of the main challenges for arbitrary-shaped text detection is to des...
Key information extraction from document images is of paramount importan...
Webly supervised learning becomes attractive recently for its efficiency...
This paper focuses on webly supervised learning (WSL), where datasets ar...
Video action detection approaches usually conduct actor-centric action
r...
The attention-based encoder-decoder framework has recently achieved
impr...
While successful in many fields, deep neural networks (DNNs) still suffe...
Feature pyramid has been an efficient method to extract features at diff...
Weakly supervised object detection (WSOD) using only image-level annotat...
Most advances in single image de-raining meet a key challenge, which is
...
This paper is about recovering the unseen future data from a given seque...
Large geometry (e.g., orientation) variances are the key challenges in t...
Matching clothing images from customers and online shopping stores has r...
Successful visual recognition networks benefit from aggregating informat...