Qinghua Hu, Bing Cao, Haiyu Yao
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.
Tiny object detection is one of the key challenges for most generic detectors. The main difficulty lies in extracting effective features of tiny objects. Existing methods usually perform generation-based feature enhancement, which is seriously affected by spurious textures and artifacts, making it difficult to make the tiny-object-specific features visible and clear for detection. To address this issue, we propose a self-reconstructed tiny object detection (SR-TOD) framework. We for the first time introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. This inspires us to enhance the weak representations of tiny objects under the guidance of the difference maps. Thus, improving the visibility of tiny objects for the detectors. Building on this, we further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear. In addition, we further propose a new multi-instance anti-UAV dataset. Extensive experiments demonstrate our effectiveness. The code is available: https://github.com/Hiyuur/SR-TOD.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.11276")
get_code_for_paper("2405.11276")
have("2405.11276")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2405.11276.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2405.11276)
Connect an agent — have() is free.