Object removal aims to eliminate undesired objects from images while plausibly restoring the underlying content with high visual fidelity. Existing diffusion-based methods often achieve strong results by relying on large-scale model finetuning, auxiliary control networks, or powerful diffusion backbones, which incur substantial computational overhead and limit practical efficiency. In this work, we propose SlimNet, a high-quality and efficient object removal framework that elicits the latent object removal capabilities of pretrained diffusion models. SlimNet injects lightweight adapters into a frozen diffusion backbone to selectively modulate intermediate representations, avoiding heavy architectural modifications. To further improve visual fidelity, we design a composite perceptual loss that enforces object removal accuracy, background preservation, and smooth boundary transitions, together with a semantic-aware data processing pipeline for automatic mask generation. Extensive experiments demonstrate that SlimNet achieves competitive removal quality compared to state-of-the-art methods, with favorable reductions in inference time and VRAM consumption, making it a practical solution for resource-constrained multimedia applications.

Although deep learning has demonstrated its outstanding performance on image classification, most well-known deep networks make efforts to optimize both their structures and their node weights for recognizing fewer (e.g., no more than 1000) object classes. Therefore, it is attractive to extend or mixture such well-known deep networks to support large-scale image classification. According to our best knowledge, how to adaptively and effectively fuse multiple CNNs for large-scale image classification is still under-explored. On this basis, a deep mixture algorithm is developed to support large-scale image classification in this paper. First, a soft spectral clustering method is developed to construct a two-layer ontology (group layer and category layer) by assigning large numbers of image categories into a set of groups according to their inter-category semantic correlations, where the semantically-related image categories under the neighbouring group nodes may share similar learning complexities. Then, such two-layer ontology is further used to generate the task groups, in which each task group contains partial image categories with similar learning complexities and one particular base deep network is learned. Finally, a gate network is learned to combine all base deep networks with fewer diverse outputs to generate a mixture network with larger outputs. Our experimental results on ImageNet10K have demonstrated that our proposed deep mixture algorithm can achieve very competitive results (top 1 accuracy: 32.13%) on large-scale image classification tasks.

Hadamard transform has played a great part in Jacket transform. Motivated by Jacket transform, we propose a simple approach for space time block codes (STBC) design by using the Hadamrd in this letter,which achieves full rate, full diversity and employs simple decoding. The orthogonal STBC may be designed easily by using the proposed approach. Especially the performance of the designed orthogonal STBC may be improved greatly.

Jacket matrices motivated by the center weight Hadamard matrices have play some important roles in signal processing and communication. In this paper we proposed a notation called block jacket matrices which substitute elements of matrices into matrices or even block matrices. Employing the well-known Pauli matrices which are very important in many subjects, several kind of block jacket matrices are constructed. Especially, construction and properties of the block jacket matrices with size 2nand 3nare investigated. Then a general approach for any size block jacket matrices is proposed. With novel properties of the block jacket matrices, a fast block inverse jacket transform is suggested.