中文标题#
魚眼目標檢測的邊緣案例合成：一種數據驅動的視角
英文标题#
Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective
中文摘要#
魚眼相機引入了顯著的失真，並對在傳統數據集上訓練的目標檢測模型提出了獨特的挑戰。 在本工作中，我們提出了一種以數據為中心的流程，通過專注於識別模型的盲點這一關鍵問題，系統地提高檢測性能。 通過詳細的錯誤分析，我們識別出關鍵的邊緣案例，如混淆的類別對、周邊失真和未充分表示的上下文。 然後我們通過邊緣案例合成直接解決這些問題。 我們微調了一個圖像生成模型，並通過精心設計的提示來引導它，生成能夠複製現實世界失敗模式的圖像。 這些合成圖像使用高質量的檢測器進行偽標記，並整合到訓練中。 我們的方法帶來了穩定的性能提升，突顯了在像魚眼目標檢測這樣的專業領域中，深入理解數據並有針對性地修復其弱點可以產生巨大的影響。
英文摘要#
Fisheye cameras introduce significant distortion and pose unique challenges to object detection models trained on conventional datasets. In this work, we propose a data-centric pipeline that systematically improves detection performance by focusing on the key question of identifying the blind spots of the model. Through detailed error analysis, we identify critical edge-cases such as confusing class pairs, peripheral distortions, and underrepresented contexts. Then we directly address them through edge-case synthesis. We fine-tuned an image generative model and guided it with carefully crafted prompts to produce images that replicate real-world failure modes. These synthetic images are pseudo-labeled using a high-quality detector and integrated into training. Our approach results in consistent performance gains, highlighting how deeply understanding data and selectively fixing its weaknesses can be impactful in specialized domains like fisheye object detection.
PDF 获取#
抖音掃碼查看更多精彩內容