Related papers: DAM: Domain-Aware Module for Multi-Domain Dataset …

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and…

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of…

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…

Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose…

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information…

We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to…

Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…

High-resolution remote sensing imagery increasingly contains dense clusters of tiny objects, the detection of which is extremely challenging due to severe mutual occlusion and limited pixel footprints. Existing detection methods typically…

Neighborhood-aware tokenized graph Transformers have recently shown great potential for node classification tasks. Despite their effectiveness, our in-depth analysis of neighborhood tokens reveals two critical limitations in the existing…

Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize…

To prevent unintentional data leakage, research community has resorted to data generators that can produce differentially private data for model training. However, for the sake of the data privacy, existing solutions suffer from either…

Magnetic resonance (MR) imaging, including cardiac MR, is prone to domain shift due to variations in imaging devices and acquisition protocols. This challenge limits the deployment of trained AI models in real-world scenarios, where…

Labeled time-series data is often expensive and difficult to obtain, making it challenging to train accurate machine learning models for real-world applications such as anomaly detection or fault diagnosis. The scarcity of labeled samples…

Deep Learning (DL) models proved themselves to perform extremely well on a wide variety of learning tasks, as they can learn useful patterns from large data sets. However, purely data-driven models might struggle when very difficult…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Most nighttime semantic segmentation studies are based on domain adaptation approaches and image input. However, limited by the low dynamic range of conventional cameras, images fail to capture structural details and boundary information in…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including…

In the semiconductor sector, due to high demand but also strong and increasing competition, time to market and quality are key factors in securing significant market share in various application areas. Thanks to the success of deep learning…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…