论文标题
实例感知，以上下文为中心和记忆有效的弱监督对象检测
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
论文作者
论文摘要
通过减少培训期间对强大监督的需求，弱监督的学习已成为一种引人注目的对象检测工具。但是，仍然面临重大挑战：（1）对象实例的差异可能是模棱两可的； （2）探测器倾向于专注于区分零件，而不是整个对象； （3）如果没有地面真理，对物体提案必须多余，以供高度召回，从而导致大量的记忆消耗。解决这些挑战是困难的，因为它通常需要消除不确定性和琐碎的解决方案。为了解决这些问题，我们开发了一个以实例感知和以上下文为中心的统一框架。它采用实例感知的自我训练算法和可学习的混凝土下降块，同时设计记忆有效的顺序批次批次后传播。我们提出的方法可以在可可（$ 12.1 \％〜ap $，$ 24.8 \％〜AP_ {50} $）上实现最先进的结果，VOC 2007（$ 54.9 \％〜AP $）和VOC 2012（$ 52.1 \％〜AP $），通过极大的利润来提高载量。此外，提出的方法是第一个基于基准重新系统的模型和弱监督的视频对象检测的方法。代码，模型和更多详细信息将在以下网址提供：https：//github.com/nvlabs/wetectron。
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires to eliminate uncertainties and trivial solutions. To target these issues we develop an instance-aware and context-focused unified framework. It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation. Our proposed method achieves state-of-the-art results on COCO ($12.1\% ~AP$, $24.8\% ~AP_{50}$), VOC 2007 ($54.9\% ~AP$), and VOC 2012 ($52.1\% ~AP$), improving baselines by great margins. In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection. Code, models, and more details will be made available at: https://github.com/NVlabs/wetectron.
