Related papers: Beyond [cls]: Exploring the true potential of Mask…
With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or…
SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perform sub-optimally when used for linear probing. We propose an…
Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs. Current VLP approaches differ on (i) model architecture (especially image embedders), (ii) loss functions, and (iii)…
Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the…
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked…
Image Compression for Machines (ICM) aims to compress images for machine vision tasks rather than human viewing. Current works predominantly concentrate on high-level tasks like object detection and semantic segmentation. However, the…
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience. Our…
Influence maximization (IM) is formulated as selecting a set of initial users from a social network to maximize the expected number of influenced users. Researchers have made great progress in designing various traditional methods, and…
Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) complicates the path…
Mass spectrometry, especially so-called tandem mass spectrometry, is commonly used to assess the chemical diversity of samples. The resulting mass fragmentation spectra are representations of molecules of which the structure may have not…
Self-supervised learning (SSL) has improved empirical performance by unleashing the power of unlabeled data for practical applications. Specifically, SSL extracts the representation from massive unlabeled data, which will be transferred to…
While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient…
Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhanced data storage capacity but also potentially brings…
Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…
Multiplex influence maximization (MIM) asks us to identify a set of seed users such as to maximize the expected number of influenced users in a multiplex network. MIM has been one of central research topics, especially in nowadays social…
Learning representations through self-supervision on unlabeled data has proven highly effective for understanding diverse images. However, remote sensing images often have complex and densely populated scenes with multiple land objects and…
The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed…
Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited scenarios. However, this approach introduces a trade-off…
Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various…
Masked Autoencoders (MAE) have been prevailing paradigms for large-scale vision representation pre-training. By reconstructing masked image patches from a small portion of visible image regions, MAE forces the model to infer semantic…