TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation

Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly large networks, inflating training and deployment costs. Motivated by recent advances in inference-time scaling for generative modeling, we propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS), a unified framework that integrates early-split multi-loss supervision, shared-parameter design, and dynamic inference repetitions. TISDiSS enables flexible speed-performance trade-offs by adjusting inference depth without retraining additional models. We further provide systematic analyses of architectural and training choices and show that training with more inference repetitions improves shallow-inference performance, benefiting low-latency applications. Experiments on standard speech separation benchmarks demonstrate state-of-the-art performance with a reduced parameter count, establishing TISDiSS as a scalable and practical framework for adaptive source separation.

Near-Field SAR Image Restoration Based On Two Dimensional Spatial-Variant Deconvolution

Images of near-field SAR contains spatial-variant sidelobes and clutter, subduing the image quality. Current image restoration methods are only suitable for small observation angle, due to their assumption of 2D spatial-invariant degradation operation. This limits its potential for large-scale objects imaging, like the aircraft. To ease this restriction, in this work an image restoration method based on the 2D spatial-variant deconvolution is proposed. First, the image degradation is seen as a complex convolution process with 2D spatial-variant operations. Then, to restore the image, the process of deconvolution is performed by cyclic coordinate descent algorithm. Experiments on simulation and measured data validate the effectiveness and superiority of the proposed method. Compared with current methods, higher precision estimation of the targets' amplitude and position is obtained.