- TL;DR: This work proposes a novel ConvNet architecture and a two-stage training scheme for class-specific object boundary estimation with improved performance levels.
- Abstract: This work addresses class-specific object boundary extraction, i.e., retrieving boundary pixels that belong to a class of objects in the given image. Although recent ConvNet-based approaches demonstrate impressive results, we notice that they produce several false-alarms and misdetections when used in real-world applications. We hypothesize that although boundary detection is simple at some pixels that are rooted in identifiable high-frequency locations, other pixels pose a higher level of difficulties, for instance, region pixels with an appearance similar to the boundaries; or boundary pixels with insignificant edge strengths. Therefore, the training process needs to account for different levels of learning complexity in different regions to overcome false alarms. In this work, we devise a curriculum-learning-based training process for object boundary detection. This multi-stage training process first trains the network at simpler pixels (with sufficient edge strengths) and then at harder pixels in the later stages of the curriculum. We also propose a novel system for object boundary detection that relies on a fully convolutional neural network (FCN) and wavelet decomposition of image frequencies. This system uses high-frequency bands from the wavelet pyramid and augments them to conv features from different layers of FCN. Our ablation studies with contourMNIST dataset, a simulated digit contours from MNIST, demonstrate that this explicit high-frequency augmentation helps the model to converge faster. Our model trained by the proposed curriculum scheme outperforms a state-of-the-art object boundary detection method by a significant margin on a challenging aerial image dataset.
- Keywords: Computer Vision, Object Contour Detection, Curriculum Learning, Wavelets, Aerial Imagery