Figure 2. Overall architecture of MFuser. MFuser takes inputs through both VFM and VLM visual encoders. Features from each encoder
layer are concatenated and refined in MVFuser, which captures sequential and spatial dependencies in parallel. The refined features are
then added back to the original features and passed to the next layer. MTEnhancer strengthens text embeddings of each class by integrating
visualfeaturesthroughahybridattention-Mambamechanism. TheenhancedtextembeddingsserveasobjectqueriesfortheMask2Former
decoder, alongside multi-scale visual features. During training, only MVFusers, MTEnhancers, and the segmentation decoder are trainable
while the VFM and VLM remain frozen, preserving their generalization ability and enabling efficient training. Note that skip connections
between each block of MTEnhancer are omitted for clarity.