Referring image segmentation (RIS) aims to locate the particular region corresponding to the language expression. Existing methods incorporate features from different modalities in a bottom-up manner. This design may get some unnecessary image-text pairs, which leads to an inaccurate segmentation mask. In this paper, we propose a referring image segmentation method called HARIS, which introduces the Human-Like Attention mechanism and uses the parameter-efficient fine-tuning (PEFT) framework. To be specific, the Human-Like Attention gets a feedback signal from multi-modal features, which makes the network center on the specific objects and discard the irrelevant image-text pairs. Besides, we introduce the PEFT framework to preserve the zero-shot ability of pre-trained encoders. Extensive experiments on three widely used RIS benchmarks and the PhraseCut dataset demonstrate that our method achieves state-of-the-art performance and great zero-shot ability.

Super-resolution is essential in improving the image quality of Magnetic Resonance Imaging (MRI). Existing MRI Super-Resolution methods leverage multi-contrast MRI and achieve satisfied effects. However, these methods perform alignment by calculating the similarity of single-scale semantic features between reference images and low-resolution images, which causes misalignment and limits the performance of MRI Super-Resolution. To tackle this problem, we propose the Flexible Alignment Super-resolution Network (FASR-Net) for multi-contrast MRI Super-resolution, which explores the interaction of multi-scale features. To this end, we first use the feature extractor to generate multi-scale features, including hierarchical features and semantic pyramid features. Subsequently, we introduce the Hierarchical-Feature Alignment (HF) module and the Semantic-Pyramid-Feature Alignment (SF) module to align hierarchical features and semantic pyramid features, respectively. Finally, the Cross-Hierarchical Progressive Fusion (CHPF) module fuses these aligned features at different scales, which further improves the model's performance. Extensive experiments on FastMRI and IXI datasets show that FASR-net achieves the most competitive results over state-of-the-art approaches. Our code will be available atFASR-Net.