High-precision image segmentation based on a hybrid CNN–Transformer architecture

CMT-UNet: enhancing remote sensing image segmentation via a hybrid CNN-Mamba-transformer architecture

DenseSwinLight: A Hybrid CNN–Transformer Model with Lightweight Post-hoc Fusion for Visual Explainability

The Hybrid CNN–Transformer architectures offer high-performance image analysis by combining local extraction and global contextual modeling. However, this integration complicates decision-making mechanisms and increases the opacity of models, making them difficult for human users to interpret. We propose DenseSwinLight, a hybrid approach that combines convolution-based feature extraction using DenseNet201 and global contextual modeling using the Swin Transformer V2-Large to simultaneously enhance local discrimination and global context. Beyond performance, the goal of this work is to make the model's decisions more transparent. We introduce a post-hoc explainability module based on the fusion of two complementary sources of evidence, namely a Grad-CAM map from the CNN branch and a proxy attention map. The fusion is learned by an extremely lightweight MLP fusion module, consisting of only 65 parameters, and constrained by area, total variation, and entropy regularizations to produce a parsimonious and stable explanatory mask. Evaluated on a real dataset acquired in an uncontrolled environment covering six classes (Bacteria, Fungi, Healthy, Pest, Phytophthora, and Virus), DenseSwinLight achieves an accuracy of 98.96% on the test set with Test-Time Augmentation, and a macro F1 score of 0.9897. The fusion module achieves a combined soft fidelity score of 0.498 and 0.513 in hard mode according to the insertion and deletion curves, for an average mask area of 0.12. These results confirm the model's ability to provide robust predictions while producing compact and actionable visual explanations for human interpretation.

LightVM-SparseUNet: a lightweight medical image segmentation framework via Vision Mamba and sparse attention

Experimental results demonstrate that LightVM-SparseUNet achieves segmentation competitive with state-of-the-art large-scale models across two authoritative public datasets.

AKNet: an aligned kernel network for image restoration

An efficient aligned kernel network (AKNet) is proposed, which innovatively employs super-large convolution kernels to capture global receptive fields with minimal computational overhead, effectively mimicking the long-range dependency modeling of transformers.

GLA-DesnowNet: A Lightweight Hybrid CNN–Transformer Architecture for Image Snow Removal

Single-image snow removal remains a challenging, ill-posed inverse problem in computer vision due to the highly variable appearance of snow degradation. Existing CNN-based methods are limited by local receptive fields and cannot model globally distributed snow patterns, while Transformer-based methods achieve strong performance at a prohibitive computational cost. To address both limitations, GLA-DesnowNet is proposed as a lightweight hybrid architecture that introduces a novel Gated Transformer (GT) module, a gated global attention mechanism designed specifically for physics-driven image desnowing. The Gated Transformer applies global multi-head self-attention with a learned convolutional gate, enabling long-range spatial dependencies to be captured while remaining computationally efficient. An adaptive three-channel snow-mask generation strategy is introduced to automatically produce pixel-level supervision from paired images without manual annotation. A compound loss combining L1 reconstruction with multi-scale pyramid loss is employed to ensure consistent restoration across spatial scales. Evaluated on the Snow100K benchmark, the proposed method achieves 29.30 dB PSNR and 0.93 SSIM in only 160 training epochs, with 0.53 M parameters and 4.44 GFLOPs per inference—significantly fewer than existing state-of-the-art (SOTA) methods—while maintaining competitive restoration quality. On the Comprehensive Snow Dataset (CSD), the identical model achieves a 27.79 dB PSNR and 0.90 SSIM. These results confirm a strong efficiency–accuracy trade-off and cross-dataset generalization suited for resource-constrained and real-time deployment.

A Deformable Hybrid Transformer With Multi-Axis Strip Attention for Geometric-Aware Medical Image Diagnosis

Accurate diagnosis in medical imaging is often hampered by two intrinsic factors: the complex, anomalous geometric distortion of anatomical structures and the extreme size variability of pathological lesions. Existing convolutional neural networks (CNNs) struggle with global context, while Vision Transformer (ViT) models are limited by quadratic computational costs or reliance on window-based attention mechanisms that disrupt semantic continuity. To address these limitations, we propose MaxStripViT, a novel hybrid architecture that effectively integrates distortion modeling with multi-axis strip attention mechanisms and Local Position-Aware blocks. Our method introduces three key contributions: 1) geometric-adaptive stem (GAS) leverages learnable offsets via Deformable Convolutions (DCNv2) to dynamically align the sampling grid with irregular organ boundaries at the earliest feature extraction stage. It effectively mitigates background noise; 2) position-aware local block is proposed to enhance the Mobile Inverted Bottleneck (MBConv) with Coordinate Attention. This mechanism explicitly models long-range dependencies along spatial axes, improving the precise localization of subtle lesions; and 3) novel sequential multi-axis strip attention mechanism is proposed to replace shift window-based self-attention. The proposed method is experimented on three dataset benchmarks of CT and ChestXray imaging for multi-class lung disease such as CheXtImageNet, IQ-OTH/NCCD, and ChestXray-Image dataset. The results demonstrated that MaxStripViT achieves robust performance and outperforms standard ViT models, and improves performance compared to the most advanced hybrid models currently available, including Swin Transformer, MaxViT, CSWin, ConvNeXt, ConvNeXtv2, and EfficientNet-B7, in terms of classification accuracy and computational efficiency. The proposed method provides a robust solution for health scenarios requiring both geometric flexibility and multi-scale interpretability.