State-of-the-art approaches for crowd counting resort to deep neural networks to predict density maps. However, counting people in congested scenes remains a challenging task because counting accuracy can be seriously degraded by the presence of drastic scale variation, density inconsistency, and complex background. To battle this ingrained issue, we propose in this paper a novel and powerful network called Scale Tree Network (STNet) for accurate crowd counting. STNet consists of two key components: a Scale-Tree Diversity Enhancer and a Multi-level Auxiliator. Specifically, the Diversity Enhancer is designed to enrich scale diversity, which alleviates limitations of existing methods caused by insufficient level of scales. A novel tree structure is adopted to hierarchically parse coarse-to-fine crowd regions. Furthermore, a simple yet effective Multi-level Auxiliator is presented to aid in exploiting generalisable shared characteristics at multiple levels, allowing more accurate pixel-wise background cognition. The overall STNet is trained in an end-to-end manner, without the needs for manually tuning loss weights between the main and the auxiliary tasks. Extensive experiments on five challenging crowd datasets demonstrate the superiority of the proposed method.

We introduce BSD-GAN, a novel multi-branch and scale-disentangled training method which enables unconditional Generative Adversarial Networks (GANs) to learn image representations at multiple scales, benefiting a wide range of generation and editing tasks. The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features. Specifically, each noise vector, as input to the generator network of BSD-GAN, is deliberately split into several sub-vectors, each corresponding to, and is trained to learn, image representations at a particular scale. During training, we progressively “de-freeze” the sub-vectors, one at a time, as a new set of higher-resolution images is employed for training and more network layers are added. A consequence of such an explicit sub-vector designation is that we can directly manipulate and even combine latent (sub-vector) codes which model different feature scales. Extensive experiments demonstrate the effectiveness of our training method in scale-disentangled learning of image representations and synthesis of novel image contents, without any extra labels and without compromising quality of the synthesized high-resolution images. We further demonstrate several image generation and manipulation applications enabled or improved by BSD-GAN.

Convolutional neural networks (CNNs) have demonstrated great success in vision tasks. However, most existing architectures still suffer from low feature reuse efficiency. In this paper, we present a layer attention based Adaptively Dense Network (ADNet) by adaptively determining the reuse status of hierarchical preceding features. Specifically, a dense residual aggregation strategy is developed to fuse multi-level internal representations in an effective manner. Furthermore, a novel layer attention mechanism is proposed to explicitly model the interrelationship among layers to automatically adjust the density of the network. It is worth noting that existing ResNets and DenseNets are both special cases of our ADNet. Extensive experiments demonstrate that the proposed architecture consistently and indubitably achieves competitive results in accuracy on benchmark datasets (CIFAR10, CIFAR100, and SVHN), while at the same time remarkably reduces computational costs and memory space. Visualization and analysis on layer-wise attention further provide better understanding on the density of feature reuse in Deep Networks.