Related papers: Masked Collaborative Contrast for Weakly Supervise…

Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar (from two different domains) for leveraging detailed exemplar styles to achieve realistic image translation. Existing work builds…

In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either…

The global reach of social media has amplified the spread of hateful content, including implicit sexism, which is often overlooked by conventional detection methods. In this work, we introduce an Adaptive Supervised Contrastive lEarning…

Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in…

Predicting socioeconomic indicators within urban regions is crucial for fostering inclusivity, resilience, and sustainability in cities and human settlements. While pioneering studies have attempted to leverage multi-modal data for…

Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Contextrast, a contrastive learning-based semantic…

In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training self-supervised depth estimation. We argue that the…

As the remarkable development of facial manipulation technologies is accompanied by severe security concerns, face forgery detection has become a recent research hotspot. Most existing detection methods train a binary classifier under…

For medical image segmentation, contrastive learning is the dominant practice to improve the quality of visual representations by contrasting semantically similar and dissimilar pairs of samples. This is enabled by the observation that…

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters…

Heterogeneous graph neural networks (HGNNs) have demonstrated their superiority in exploiting auxiliary information for recommendation tasks. However, graphs constructed using meta-paths in HGNNs are usually too dense and contain a large…

State-of-the-art techniques in weakly-supervised semantic segmentation (WSSS) using image-level labels exhibit severe performance degradation on driving scene datasets such as Cityscapes. To address this challenge, we develop a new WSSS…

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on…

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation…

Monocular Semantic Scene Completion (MSSC) aims to predict the voxel-wise occupancy and semantic category from a single-view RGB image. Existing methods adopt a single-stage framework that aims to simultaneously achieve visible region…

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

This paper presents a novel semantic scene change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end…

The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based…

The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing methods typically depend on the painstaking training modules, which…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…