We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN.
翻译:我们提出了一个新的未经监督的地物代表学习方法,即基于视觉常识的区域革命神经网络(VC R-CNN),作为用于字幕和VQA等高级任务的更好的视觉区域编码器。鉴于图像中一组被检测到的物体区域(例如使用快速R-CNN),如同任何其他未经监督的地物学习方法(例如,Word2vec)一样,VC R-NN的代理培训目标是预测一个区域的背景物体。然而,它们根本不同:VC R-CNN的预测是使用因果干预:P(Y ⁇ do(X)),而其他则使用常规可能性:P(Y ⁇ X)。这也是为什么VC R-CN可以学习像椅子那样的“思维”知识,而如果看到表格,则可能存在类似主席的“共同”现象。我们在三种流行任务模式中广泛应用VCR-CN的特征:图像定位、Vqu(VQ)和http-CR-Com-Proferal-Prof-Proferation A/VA)。