Related papers: Cascade Decoder: A Universal Decoding Method for B…

Depth completion recovers a dense depth map from sensor measurements. Current methods are mostly tailored for very sparse depth measurements from LiDARs in outdoor settings, while for indoor scenes Time-of-Flight (ToF) or structured light…

Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive…

The interpretability of neural networks has recently received extensive attention. Previous prototype-based explainable networks involved prototype activation in both reasoning and interpretation processes, requiring specific explainable…

We propose a new deep learning method for tumour segmentation when dealing with missing imaging modalities. Instead of producing one network for each possible subset of observed modalities or using arithmetic operations to combine feature…

In recent years, remote sensing change detection has garnered significant attention due to its critical role in resource monitoring and disaster assessment. Change detection tasks exist with different output granularities such as BCD, SCD,…

Representation of data on mixed variables, numerical and categorical types to get suitable feature map is a challenging task as important information lies in a complex non-linear manifold. The feature transformation should be able to…

Density reconstruction from X-ray projections is an important problem in radiography with key applications in scientific and industrial X-ray computed tomography (CT). Often, such projections are corrupted by unknown sources of noise and…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages. Although modern instance segmentation cascades…

Building correspondences across different modalities, such as video and language, has recently become critical in many visual recognition applications, such as video captioning. Inspired by machine translation, recent models tackle this…

U-Net is widely used in medical image segmentation due to its simple and flexible architecture design. To address the challenges of scale and complexity in medical tasks, several variants of U-Net have been proposed. In particular, methods…

Identifying biomarkers in medical images is vital for a wide range of biotech applications. However, recent Transformer and CNN based methods often struggle with variations in morphology and staining, which limits their feature extraction…

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted…

Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Following such success, in this paper, we prove that the…

Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the first time, a fully convolutional end-to-end architecture that…

Most modern face completion approaches adopt an autoencoder or its variants to restore missing regions in face images. Encoders are often utilized to learn powerful representations that play an important role in meeting the challenges of…

This paper proposes a theoretical framework on the mechanism of autoencoders. To the encoder part, under the main use of dimensionality reduction, we investigate its two fundamental properties: bijective maps and data disentangling. The…

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio, however, often contains mixed speech and background sounds,…