Related papers: Discrepancy-Aware Attention Network for Enhanced A…
To achieve promising results on blind image super-resolution (SR), some attempts leveraged the low resolution (LR) images to predict the kernel and improve the SR performance. However, these Supervised Kernel Prediction (SKP) methods are…
Deep learning brought boosts to auto diabetic retinopathy (DR) diagnosis, thus, greatly helping ophthalmologists for early disease detection, which contributes to preventing disease deterioration that may eventually lead to blindness. It…
In recent years, even though Stochastic Gradient Descent (SGD) and its variants are well-known for training neural networks, it suffers from limitations such as the lack of theoretical guarantees, vanishing gradients, and excessive…
The most of CNN based super-resolution (SR) methods assume that the degradation is known (\eg, bicubic). These methods will suffer a severe performance drop when the degradation is different from their assumption. Therefore, some approaches…
While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existing FSOD systems follow FSC approaches, ignoring critical…
Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…
Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…
Anomaly Detection involves identifying deviations from normal data distributions and is critical in fields such as medical diagnostics and industrial defect detection. Traditional AD methods typically require the availability of normal…
Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes.…
Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…
In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…
Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before. In classical ZSL algorithms, attributes are introduced as the intermediate semantic…
Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience…
Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes against domain shift problem where data of unseen classes may be misclassified as seen classes. However, existing GZSL is still limited to seen domains. In…
The challenge of long-term video understanding remains constrained by the efficient extraction of object semantics and the modelling of their relationships for downstream tasks. Although the CLIP visual features exhibit discriminative…
Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attention limit performance in dynamic scenes with occlusions,…
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the sample regions and…
Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more practical for handling data-restricted real-world…
The efficacy of multimodal learning in remote sensing (RS) is severely undermined by missing modalities. The challenge is exacerbated by the RS highly heterogeneous data and huge scale variation. Consequently, paradigms proven effective in…
Zero-shot 3D (ZS-3D) anomaly detection aims to identify defects in 3D objects without relying on labeled training data, making it especially valuable in scenarios constrained by data scarcity, privacy, or high annotation cost. However, most…