Related papers: Contextrast: Contextual Contrastive Learning for S…

While most existing segmentation methods usually combined the powerful feature extraction capabilities of CNNs with Conditional Random Fields (CRFs) post-processing, the result always limited by the fault of CRFs . Due to the notoriously…

Semantic segmentation of satellite imagery is a common approach to identify patterns and detect changes around the planet. Most of the state-of-the-art semantic segmentation models are trained in a fully supervised way using Convolutional…

Achieving artificially intelligent-native wireless networks is necessary for the operation of future 6G applications such as the metaverse. Nonetheless, current communication schemes are, at heart, a mere reconstruction process that lacks…

Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we…

Image harmonization task aims at harmonizing different composite foreground regions according to specific background image. Previous methods would rather focus on improving the reconstruction ability of the generator by some internal…

Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…

Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise semantic similarity…

Unsupervised domain adaptation (UDA) for semantic segmentation has been well-studied in recent years. However, most existing works largely neglect the local regional consistency across different domains and are less robust to changes in…

While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object…

In Computer Vision, self-supervised contrastive learning enforces similar representations between different views of the same image. The pre-training is most often performed on image classification datasets, like ImageNet, where images…

The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the…

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead…

Aspect Sentiment Triplet Extraction (ASTE) is a burgeoning subtask of fine-grained sentiment analysis, aiming to extract structured sentiment triplets from unstructured textual data. Existing approaches to ASTE often complicate the task…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…

Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotations is challenging, requiring labels for every pixel in an image. In scenarios like autonomous…

Digital histology images are amenable to the application of convolutional neural network (CNN) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches…

In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a…

Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial…

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…