Learning Modulated Loss for Rotated Object Detection
نویسندگان
چکیده
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) or eight four vertices) to describe bounding box l1 loss as function. In this paper, we argue that aforementioned integration can cause training instability performance degeneration. The main reason is discontinuity which caused by contradiction between definition We refer above issues sensitivity error (RSE) propose a modulated dismiss loss. achieve consistent improvement on parameter methods. Experimental results using one stage two stages detectors demonstrate effectiveness our integrated network achieves competitive performances several benchmarks including DOTA UCAS AOD. code available at https://github.com/yangxue0827/RotationDetection.
منابع مشابه
islanding detection methods for microgrids
امروزه استفاده از منابع انرژی پراکنده کاربرد وسیعی یافته است . اگر چه این منابع بسیاری از مشکلات شبکه را حل می کنند اما زیاد شدن آنها مسائل فراوانی برای سیستم قدرت به همراه دارد . استفاده از میکروشبکه راه حلی است که علاوه بر استفاده از مزایای منابع انرژی پراکنده برخی از مشکلات ایجاد شده توسط آنها را نیز منتفی می کند . همچنین میکروشبکه ها کیفیت برق و قابلیت اطمینان تامین انرژی مشترکان را افزایش ...
15 صفحه اولLearning visual context for object detection ∗
Kontekst ima pomembno vlogo pri splošnem zaznavanju prizorov, saj zagotavlja dodatno informacijo o možnih lokacijah objektov v slikah. Detektorji objektov, ki se uporabljajo v računalnǐskem vidu, tovrstne informacijo običajno ne izkoristijo. V članku bomo zato predstavili koncept, kako se lahko kontekstualne informacije naučimo iz primerov slik prizorov. To informacijo bomo uporabili za izračun...
متن کاملLearning Search Based Inference for Object Detection
We study the problem of visual object detection and propose a method that learns the inference procedure during training time. We propose a best-first search based inference system that is already optimized for during training. This overcomes the inherent limitation of branch&bound whose applicability relies on the availability of tight bounding functions. The optimization problem is implemente...
متن کاملActive learning for visual object detection
One of the most labor intensive aspects of developing accurate visual object detectors using machine learning is to gather sufficient amount of labeled examples. We develop a selective sampling method, based on boosting, which dramatically reduces the amount of human labor required for this task. We apply this method to the problem of detecting pedestrians from a video camera mounted on a movin...
متن کاملLearning Region Features for Object Detection
While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely handcrafted, featured by RoI pooling methods. This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable. The proposed method removes most heuristic choices and outperforms its RoI pooling co...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2021
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v35i3.16347