Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods
Representation learning with small labeled data have emerged in many problems, since the
success of deep neural networks often relies on the availability of a huge amount of labeled …
success of deep neural networks often relies on the availability of a huge amount of labeled …
Wave-vit: Unifying wavelet and transformers for visual representation learning
Abstract Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for
computer vision tasks, while the self-attention computation in Transformer scales …
computer vision tasks, while the self-attention computation in Transformer scales …
Unsupervised embedding learning via invariant and spreading instance feature
This paper studies the unsupervised embedding learning problem, which requires an
effective similarity measurement between samples in low-dimensional embedding space …
effective similarity measurement between samples in low-dimensional embedding space …
Invariant information clustering for unsupervised image classification and segmentation
We present a novel clustering objective that learns a neural network classifier from scratch,
given only unlabelled data samples. The model discovers clusters that accurately match …
given only unlabelled data samples. The model discovers clusters that accurately match …
Approximating cnns with bag-of-local-features models works surprisingly well on imagenet
Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven
notoriously difficult to understand how they reach their decisions. We here introduce a high …
notoriously difficult to understand how they reach their decisions. We here introduce a high …
Unsupervised representation learning by predicting image rotations
Over the last years, deep convolutional neural networks (ConvNets) have transformed the
field of computer vision thanks to their unparalleled capacity to learn high level semantic …
field of computer vision thanks to their unparalleled capacity to learn high level semantic …
Learning operators with coupled attention
Supervised operator learning is an emerging machine learning paradigm with applications
to modeling the evolution of spatio-temporal dynamical systems and approximating general …
to modeling the evolution of spatio-temporal dynamical systems and approximating general …
Photorealistic style transfer via wavelet transforms
Recent style transfer models have provided promising artistic results. However, given a
photograph as a reference style, existing methods are limited by spatial distortions or …
photograph as a reference style, existing methods are limited by spatial distortions or …
Image classification with small datasets: Overview and benchmark
Image classification with small datasets has been an active research area in the recent past.
However, as research in this scope is still in its infancy, two key ingredients are missing for …
However, as research in this scope is still in its infancy, two key ingredients are missing for …
PHA: Patch-wise high-frequency augmentation for transformer-based person re-identification
Although recent studies empirically show that injecting Convolutional Neural Networks
(CNNs) into Vision Transformers (ViTs) can improve the performance of person re …
(CNNs) into Vision Transformers (ViTs) can improve the performance of person re …