Image classification is a longstanding problem in computer vision and ma...
Semi-Supervised image classification is one of the most fundamental prob...
Human-Object Interaction (HOI) detection is a challenging computer visio...
We investigate the potential of GPT-4~\cite{gpt4} to perform Neural
Arch...
Recent breakthroughs in semi-supervised semantic segmentation have been
...
Recently, community has paid increasing attention on model scaling and
c...
Vision transformers (ViTs) are usually considered to be less light-weigh...
We present an efficient approach for Masked Image Modeling (MIM) with
hi...
Unlike existing knowledge distillation methods focus on the baseline
set...
While the deep learning techniques promote the rapid development of the
...
Self-supervised learning (SSL) has made enormous progress and largely
na...
Searching for a more compact network width recently serves as an effecti...
Structural re-parameterization (Rep) methods achieve noticeable improvem...
Self-supervised Learning (SSL) including the mainstream contrastive lear...
Learning with few labeled data has been a longstanding problem in the
co...
Evaluation metrics in machine learning are often hardly taken as loss
fu...
Training a good supernet in one-shot NAS methods is difficult since the
...
Unsupervised visual representation learning has gained much attention fr...
Self-supervised Learning (SSL) including the mainstream contrastive lear...
Recently, transformers have shown great superiority in solving computer
...
In one-shot weight sharing for NAS, the weights of each operation (at ea...
Searching for a more compact network width recently serves as an effecti...
One-shot neural architecture search (NAS) methods significantly reduce t...
Searching for network width is an effective way to slim deep neural netw...
Most differentiable neural architecture search methods construct a super...
Differentiable neural architecture search (DARTS) has gained much succes...
To deploy a well-trained CNN model on low-end computation edge devices, ...
Quantum error mitigation techniques are at the heart of quantum computat...
Neural architecture search (NAS) aims to produce the optimal sparse solu...
Differentially private (DP) learning, which aims to accurately extract
p...
Training a supernet matters for one-shot neural architecture search (NAS...
Compressing giant neural networks has gained much attention for their
ex...
This paper presents privileged multi-label learning (PrML) to explore an...
Here we study the extreme visual recovery problem, in which over 90% of
...
It is challenging to handle a large volume of labels in multi-label lear...