Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network

Transformer-based architectures have shown great success in image captioning, where object regions are encoded and then attended into the vectorial representations to guide the caption decoding. However, such vectorial representations only contain region-level information without considering the global information reflecting the entire image, which fails to expand the capability of complex multi-modal reasoning in image captioning. In this paper, we introduce a Global Enhanced Transformer (termed GET) to enable the extraction of a more comprehensive global representation, and then adaptively guide the decoder to generate high-quality captions. In GET, a Global Enhanced Encoder is designed for the embedding of the global feature, and a Global Adaptive Decoder are designed for the guidance of the caption generation. The former models intra- and inter-layer global representation by taking advantage of the proposed Global Enhanced Attention and a layer-wise fusion module. The latter contains a Global Adaptive Controller that can adaptively fuse the global information into the decoder to guide the caption generation. Extensive experiments on MS COCO dataset demonstrate the superiority of our GET over many state-of-the-arts.

Learning Efficient GANs using Differentiable Masks and co-Attention Distillation

Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computational and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to GANs due to the complicated generator architecture and the unstable adversarial training. To solve these, in this paper, we introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. The former searches for a light-weight generator architecture in a training-adaptive manner. To overcome channel inconsistency when pruning the residual connections, an adaptive cross-block group sparsity is further incorporated. The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model. Experiments show that DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model. Code is available at https://github.com/SJLeo/DMAD.

Rotated Binary Neural Network

Binary Neural Network (BNN) shows its predominance in reducing the complexity of deep neural networks. However, it suffers severe performance degradation. One of the major impediments is the large quantization error between the full-precision weight vector and its binary vector. Previous works focus on compensating for the norm gap while leaving the angular bias hardly touched. In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version. At the beginning of each training epoch, we propose to rotate the full-precision weight vector to its binary vector to reduce the angular bias. To avoid the high complexity of learning a large rotation matrix, we further introduce a bi-rotation formulation that learns two smaller rotation matrices. In the training stage, we devise an adjustable rotated weight vector for binarization to escape the potential local optimum. Our rotation leads to around 50% weight flips which maximize the information gain. Finally, we propose a training-aware approximation of the sign function for the gradient backward. Experiments on CIFAR-10 and ImageNet demonstrate the superiorities of RBNN over many state-of-the-arts. Our source code, experimental settings, training logs and binary models are available at https://github.com/lmbxmu/RBNN.

Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters

Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters. However, on public cloud clusters, due to the moderate inter-connection bandwidth between instances, traditional state-of-the-art distributed training systems cannot scale well in training large-scale models. In this paper, we propose a new computing and communication efficient top-k sparsification communication library for distributed training. To further improve the system scalability, we optimize I/O by proposing a simple yet efficient multi-level data caching mechanism and optimize the update operation by introducing a novel parallel tensor operator. Experimental results on a 16-node Tencent Cloud cluster (each node with 8 Nvidia Tesla V100 GPUs) show that our system achieves 25%-40% faster than existing state-of-the-art systems on CNNs and Transformer. We finally break the record on DAWNBench on training ResNet-50 to 93% top-5 accuracy on ImageNet.

Channel Pruning via Automatic Structure Search

Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combinations of pruned structure for deep networks, we first propose to shrink the combinations where the preserved channels are limited to a specific space, thus the combinations of pruned structure can be significantly reduced. And then, we formulate the search of optimal pruned structure as an optimization problem and integrate the ABC algorithm to solve it in an automatic manner to lessen human interference. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner. Experiments on CIFAR-10 show that ABCPruner reduces 73.68\% of FLOPs and 88.68\% of parameters with even 0.06\% accuracy improvement for VGGNet-16. On ILSVRC-2012, it achieves a reduction of 62.87\% FLOPs and removes 60.01\% of parameters with negligible accuracy cost for ResNet-152. The source codes can be available at https://github.com/lmbxmu/ABCPruner.

Semi-Supervised Adversarial Monocular Depth Estimation

In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth , i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can (1) improve most state-of-the-art models on the NYUD v2 dataset by effectively leveraging additional unlabeled data sources; (2) reach state-of-the-art accuracy when the training set is small, e.g., on the Make3D dataset; (3) adapt well to an unseen new dataset (Make3D in our case) after training on an annotated dataset (KITTI in our case).

Dynamic Distribution Pruning for Efficient Network Architecture Search

Network architectures obtained by Neural Architecture Search (NAS) have shown state-of-the-art performance in various computer vision tasks. Despite the exciting progress, the computational complexity of the forward-backward propagation and the search process makes it difficult to apply NAS in practice. In particular, most previous methods require thousands of GPU days for the search process to converge. In this paper, we propose a dynamic distribution pruning method towards extremely efficient NAS, which samples architectures from a joint categorical distribution. The search space is dynamically pruned every a few epochs to update this distribution, and the optimal neural architecture is obtained when there is only one structure remained. We conduct experiments on two widely-used datasets in NAS. On CIFAR-10, the optimal structure obtained by our method achieves the state-of-the-art $1.9$\% test error, while the search process is more than $1,000$ times faster (only $1.5$ GPU hours on a Tesla V100) than the state-of-the-art NAS algorithms. On ImageNet, our model achieves 75.2\% top-1 accuracy under the MobileNet settings, with a time cost of only $2$ GPU days that is $100\%$ acceleration over the fastest NAS algorithm. The code is available at \url{ https://github.com/tanglang96/DDPNAS}

Dynamic Neural Network Decoupling

Convolutional neural networks (CNNs) have achieved a superior performance by taking advantages of the complex network architectures and huge numbers of parameters, which however become uninterpretable and challenge their full potential to practical applications. Towards better understand the rationale behind the network decisions, we propose a novel architecture decoupling method, which dynamically discovers the hierarchical path consisting of activated filters for each input image. In particular, architecture controlling module is introduced in each layer to encode the network architecture and identify the activated filters corresponding to the specific input. Then, mutual information between architecture encoding and the attribute of input image is maximized to decouple the network architecture, and subsequently disentangles the filters by limiting the outputs of filter during training. Extensive experiments show that several merits have been achieved based on the proposed architecture decoupling, i.e., interpretation, acceleration and adversarial attacking.