OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers
This addresses the problem of segmenting camouflaged objects in images for computer vision applications, representing an incremental improvement over two-stage methods.
The paper tackles camouflaged instance segmentation by proposing OSFormer, a one-stage transformer framework that achieves 41% AP with only 3,040 training samples under 60 epochs.
We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS). OSFormer is based on two key designs. First, we design a location-sensing transformer (LST) to obtain the location label and instance-aware parameters by introducing the location-guided queries and the blend-convolution feedforward network. Second, we develop a coarse-to-fine fusion (CFF) to merge diverse context information from the LST encoder and CNN backbone. Coupling these two components enables OSFormer to efficiently blend local features and long-range context dependencies for predicting camouflaged instances. Compared with two-stage frameworks, our OSFormer reaches 41% AP and achieves good convergence efficiency without requiring enormous training data, i.e., only 3,040 samples under 60 epochs. Code link: https://github.com/PJLallen/OSFormer.