Related papers: AstroMAE: Redshift Prediction Using a Masked Autoe…
This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…
The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i.e. regions not visible to the sensor. We demonstrate how these inherent sampling properties can be effectively utilized for self-supervised…
Photometric redshifts (photo-z's) provide an alternative way to estimate the distances of large samples of galaxies and are therefore crucial to a large variety of cosmological problems. Among the various methods proposed over the years,…
We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities,…
The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets. Unsupervised learning does not require labels and is more suitable for solving medical image…
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…
Monocular 3D object detection aims for precise 3D localization and identification of objects from a single-view image. Despite its recent progress, it often struggles while handling pervasive object occlusions that tend to complicate and…
This paper introduces the Efficient Decoupled Masked Autoencoder (EDMAE), a novel self-supervised method for recognizing standard views in pediatric echocardiography. EDMAE introduces a new proxy task based on the encoder-decoder structure.…
Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…
Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance…
Self-supervised pretraining has transformed computer vision by enabling data-efficient fine-tuning, yet high-resolution training typically requires server-scale infrastructure, limiting in-domain foundation model development for many…
The accurate segmentation of lesions in whole-body PET/CT imaging is es-sential for tumor characterization, treatment planning, and response assess-ment, yet current manual workflows are labor-intensive and prone to inter-observer…
Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing…
Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational…
Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…
Machine learning (ML) has become a key tool in astronomy, driving advancements in the analysis and interpretation of complex datasets from observations. This article reviews the application of ML techniques in the identification and…
We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks…
Crystal structure forms the foundation for understanding the physical and chemical properties of materials. Generative models have emerged as a new paradigm in crystal structure prediction(CSP), however, accurately capturing key…
Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and…