Related papers: Spatial Frequency Modulation for Semantic Segmenta…
Video semantic segmentation aims to generate accurate semantic maps for each video frame. To this end, many works dedicate to integrate diverse information from consecutive frames to enhance the features for prediction, where a feature…
Infrared and visible image fusion aims to utilize the complementary information from two modalities to generate fused images with prominent targets and rich texture details. Most existing algorithms only perform pixel-level or feature-level…
In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation…
Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…
Image-level weakly supervised semantic segmentation (WSSS) is a fundamental yet challenging computer vision task facilitating scene understanding and automatic driving. Most existing methods resort to classification-based Class Activation…
Accurate upsampling of Head-Related Transfer Functions (HRTFs) from sparse measurements is crucial for personalized spatial audio rendering. Traditional interpolation methods, such as kernel-based weighting or basis function expansions,…
Time-frequency domain dual-path models have demonstrated strong performance and are widely used in source separation. Because their computational cost grows with the number of frequency bins, these models often use the band-split (BS)…
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…
Pixel-wise predictions are required in a wide variety of tasks such as image restoration, image segmentation, or disparity estimation. Common models involve several stages of data resampling, in which the resolution of feature maps is first…
The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods.…
Generalized spatial modulation (GSM) uses $n_t$ transmit antenna elements but fewer transmit radio frequency (RF) chains, $n_{rf}$. Spatial modulation (SM) and spatial multiplexing are special cases of GSM with $n_{rf}=1$ and $n_{rf}=n_t$,…
Image deblurring aims to reconstruct a latent sharp image from its corresponding blurred one. Although existing methods have achieved good performance, most of them operate exclusively in either the spatial domain or the frequency domain,…
We propose Semantic-Fast-SAM (SFS), a semantic segmentation framework that combines the Fast Segment Anything model with a semantic labeling pipeline to achieve real-time performance without sacrificing accuracy. FastSAM is an efficient…
Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation…
We propose Frequency-Guided Attention (FGA), a lightweight upsampling module for single image super-resolution. Conventional upsamplers, such as Sub-Pixel Convolution, are efficient but frequently fail to reconstruct high-frequency details…
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and…
Massive MIMO, a candidate for 5G technology, promises significant gains in wireless data rates and link reliability by using large numbers of antennas (more than 64) at the base transceiver station (BTS). Extra antennas help by focusing the…
Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on…
Image restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods primarily focus on the spatial domain, neglecting the understanding of frequency variations and ignoring the impact of implicit…
Spatial modulation (SM) is an innovative and promising digital modulation technology that strikes an appealing trade-off between spectral efficiency and energy efficiency with a simple design philosophy. SM enjoys plenty of benefits and…