Luc Gool, Deng-Ping Fan, He Tang, Jialun Pei, Tianyang Cheng, Chuanbo Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 OS-Former 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.02255")
get_code_for_paper("2207.02255")
have("2207.02255")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2207.02255.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2207.02255)
Connect an agent — have() is free.