Related papers: Triple-domain Feature Learning with Frequency-awar…
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the…
Industrial control systems operate in dynamic environments where traffic distributions vary across scenarios, labeled samples are limited, and unknown attacks frequently emerge, posing significant challenges to cross-domain intrusion…
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…
Few-shot classification aims to recognize novel categories with only few labeled images in each class. Existing metric-based few-shot classification algorithms predict categories by comparing the feature embeddings of query images with…
We propose a dual-domain cascade of U-nets (i.e. a "W-net") operating in both the spatial frequency and image domains to enhance low-dose CT (LDCT) images without the need for proprietary x-ray projection data. The central slice theorem…
To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their…
In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can…
Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by using unlabeled target domain and labeled source domain data, however, in the medical domain, target domain data may not always be…
Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges…
Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream methods are dominated by…
The objective of Few-shot learning is to fully leverage the limited data resources for exploring the latent correlations within the data by applying algorithms and training a model with outstanding performance that can adequately meet the…
Cross-domain object detection and semantic segmentation have witnessed impressive progress recently. Existing approaches mainly consider the domain shift resulting from external environments including the changes of background, illumination…
Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplored for 3D point clouds. Existing methods suffer from catastrophic forgetting or…
Computer vision researchers have extensively worked on fundamental infrared visual recognition for the past few decades. Among various approaches, deep learning has emerged as the most promising candidate. However, Infrared Small Object…
Face signatures, including size, shape, texture, skin tone, eye color, appearance, and scars/marks, are widely used as discriminative, biometric information for access control. Despite recent advancements in facial recognition systems,…
Temporal action detection aims to locate and classify actions in untrimmed videos. While recent works focus on designing powerful feature processors for pre-trained representations, they often overlook the inherent noise and redundancy…
This paper addresses the gaze target detection problem in single images captured from the third-person perspective. We present a multimodal deep architecture to infer where a person in a scene is looking. This spatial model is trained on…
In this paper, we describe a simple strategy for mitigating variability in temporal data series by shifting focus onto long-term, frequency domain features that are less susceptible to variability. We apply this method to the human action…
Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance, which aims to identify small, low-contrast targets against complex backgrounds. However, existing methods often struggle with…
Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…