Related papers: Masked Siamese Networks for Label-Efficient Learni…

Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish…

As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…

Synthetic aperture radar (SAR) imaging technology is commonly used to provide 24-hour all-weather earth observation. However, it still has some drawbacks in SAR target classification, especially in fine-grained classification of aircraft:…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

The success of supervised deep learning models on cell recognition tasks relies on detailed annotations. Many previous works have managed to reduce the dependency on labels. However, considering the large number of cells contained in a…

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siamese network is proposed and developed based on two different…

We propose Masked Capsule Autoencoders (MCAE), the first Capsule Network that utilises pretraining in a modern self-supervised paradigm, specifically the masked image modelling framework. Capsule Networks have emerged as a powerful…

Self-supervised learning (SSL) has recently achieved tremendous empirical advancements in learning image representation. However, our understanding of the principle behind learning such a representation is still limited. This work shows…

We propose a semi-supervised network for wide-angle portraits correction. Wide-angle images often suffer from skew and distortion affected by perspective distortion, especially noticeable at the face regions. Previous deep learning based…

State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Recently, Masked Image Modeling (MIM) achieves great success in self-supervised visual recognition. However, as a reconstruction-based framework, it is still an open question to understand how MIM works, since MIM appears very different…

Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents, sticking to a fixed pattern leads to a limited vision cues…

We propose an unsupervised visual tracking method in this paper. Different from existing approaches using extensive annotated data for supervised learning, our CNN model is trained on large-scale unlabeled videos in an unsupervised manner.…

A common problem with segmentation of medical images using neural networks is the difficulty to obtain a significant number of pixel-level annotated data for training. To address this issue, we proposed a semi-supervised segmentation…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…