Layer assignment is seldom picked out as an independent research topic in neural architecture search. In this paper, for the first time, we systematically investigate the impact of different layer assignments to the network performance by building an architecture dataset of layer assignment on CIFAR-100. Through analyzing this dataset, we discover a neural inheritance relation among the networks with different layer assignments, that is, the optimal layer assignments for deeper networks always inherit from those for shallow networks. Inspired by this neural inheritance relation, we propose an efficient one-shot layer assignment search approach via inherited sampling. Specifically, the optimal layer assignment searched in the shallow network can be provided as a strong sampling priori to train and search the deeper ones in supernet, which extremely reduces the network search space. Comprehensive experiments carried out on CIFAR-100 illustrate the efficiency of our proposed method. Our search results are strongly consistent with the optimal ones directly selected from the architecture dataset. To further confirm the generalization of our proposed method, we also conduct experiments on Tiny-ImageNet and ImageNet. Our searched results are remarkably superior to the handcrafted ones under the unchanged computational budgets. The neural inheritance relation discovered in this paper can provide insights to the universal neural architecture search.
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the vanilla gates in RNN (e.g. the input gate in LSTM) suffer from the problem of gate undertraining mainly due to the saturating activation functions, which may result in failures of learning gating roles and thus the weak performance. In this paper, we propose a new gating mechanism within general gated recurrent neural networks to handle this issue. Specifically, the proposed gates directly short connect the extracted input features to the outputs of vanilla gates, denoted as refined gates. The refining mechanism allows enhancing gradient back-propagation as well as extending the gating activation scope, which, although simple, can guide RNN to reach possibly deeper minima. We verify the proposed gating mechanism on three popular types of gated RNNs including LSTM, GRU and MGU. Extensive experiments on 3 synthetic tasks, 3 language modeling tasks and 5 scene text recognition benchmarks demonstrate the effectiveness of our method.
Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1) recognizing arbitrary shaped text is still a challenging task, and 2) prevalent non-trainable pipeline strategies between text detection and text recognition will lead to suboptimal performances. To handle this incompatibility problem, in this paper we propose an end-to-end trainable text spotting approach named Text Perceptron. Concretely, Text Perceptron first employs an efficient segmentation-based text detector that learns the latent text reading order and boundary information. Then a novel Shape Transform Module (abbr. STM) is designed to transform the detected feature regions into regular morphologies without extra parameters. It unites text detection and the following recognition part into a whole framework, and helps the whole network achieve global optimization. Experiments show that our method achieves competitive performance on two standard text benchmarks, i.e., ICDAR 2013 and ICDAR 2015, and also obviously outperforms existing methods on irregular text benchmarks SCUT-CTW1500 and Total-Text.
Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even overlapping. This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy. Compared to human-designed features which have been widely used in existing research, raw waveforms contain more complete information and are more appropriate for multi-label classification. Taking raw waveforms as input, our network consists of two variants of ResNet structure which can learn a discriminative representation. To explore the information in intermediate layers, a multi-level prediction with attention structure is applied in our model. Furthermore, we design a mix-training strategy to break the performance limitation caused by the amount of training data. Experiments show that the mean average precision of the proposed audio classification system on Audio Set dataset is 37.2%. Without using extra training data, our system exceeds the state-of-the-art multi-level attention model.
Temporal action localization is an important yet challenging research topic due to its various applications. Since the frame-level or segment-level annotations of untrimmed videos require amounts of labor expenditure, studies on the weakly-supervised action detection have been springing up. However, most of existing frameworks rely on Class Activation Sequence (CAS) to localize actions by minimizing the video-level classification loss, which exploits the most discriminative parts of actions but ignores the minor regions. In this paper, we propose a novel weakly-supervised framework by adversarial learning of two modules for eliminating such demerits. Specifically, the first module is designed as a well-designed Seeded Sequence Growing (SSG) Network for progressively extending seed regions (namely the highly reliable regions initialized by a CAS-based framework) to their expected boundaries. The second module is a specific classifier for mining trivial or incomplete action regions, which is trained on the shared features after erasing the seeded regions activated by SSG. In this way, a whole network composed of these two modules can be trained in an adversarial manner. The goal of the adversary is to mine features that are difficult for the action classifier. That is, erasion from SSG will force the classifier to discover minor or even new action regions on the input feature sequence, and the classifier will drive the seeds to grow, alternately. At last, we could obtain the action locations and categories from the well-trained SSG and the classifier. Extensive experiments on two public benchmarks THUMOS'14 and ActivityNet1.3 demonstrate the impressive performance of our proposed method compared with the state-of-the-arts.
Networked video applications, e.g., video conferencing, often suffer from poor visual quality due to unexpected network fluctuation and limited bandwidth. In this paper, we have developed a Quality Enhancement Network (QENet) to reduce the video compression artifacts, leveraging the spatial and temporal priors generated by respective multi-scale convolutions spatially and warped temporal predictions in a recurrent fashion temporally. We have integrated this QENet as a standard-alone post-processing subsystem to the High Efficiency Video Coding (HEVC) compliant decoder. Experimental results show that our QENet demonstrates the state-of-the-art performance against default in-loop filters in HEVC and other deep learning based methods with noticeable objective gains in Peak-Signal-to-Noise Ratio (PSNR) and subjective gains visually.
This paper provides a new way to improve the efficiency of the REINFORCE training process. We apply it to the task of instance selection in distant supervision. Modeling the instance selection in one bag as a sequential decision process, a reinforcement learning agent is trained to determine whether an instance is valuable or not and construct a new bag with less noisy instances. However unbiased methods, such as REINFORCE, could usually take much time to train. This paper adopts posterior regularization (PR) to integrate some domain-specific rules in instance selection using REINFORCE. As the experiment results show, this method remarkably improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REINFORCE training.
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression efficiency, and also employs the generative adversarial network(GAN) with multiscale discriminators to perform the end-to-end trainable rate-distortion optimization. We compare the perceptual quality of our reconstructions with traditional compression algorithms using High-Efficiency Video Coding(HEVC) based Intra Profile and JPEG2000 on the public Cityscapes and ADE20K datasets, demonstrating the significant subjective quality improvement.
Shift operation is an efficient alternative over depthwise separable convolution. However, it is still bottlenecked by its implementation manner, namely memory movement. To put this direction forward, a new and novel basic component named Sparse Shift Layer (SSL) is introduced in this paper to construct efficient convolutional neural networks. In this family of architectures, the basic block is only composed by 1x1 convolutional layers with only a few shift operations applied to the intermediate feature maps. To make this idea feasible, we introduce shift operation penalty during optimization and further propose a quantization-aware shift learning method to impose the learned displacement more friendly for inference. Extensive ablation studies indicate that only a few shift operations are sufficient to provide spatial information communication. Furthermore, to maximize the role of SSL, we redesign an improved network architecture to Fully Exploit the limited capacity of neural Network (FE-Net). Equipped with SSL, this network can achieve 75.0% top-1 accuracy on ImageNet with only 563M M-Adds. It surpasses other counterparts constructed by depthwise separable convolution and the networks searched by NAS in terms of accuracy and practical speed.
This paper proposes an unified framework for efficiently spotting scene text in videos. The method localizes and tracks text in each frame, and recognizes each tracked text stream one-time. Specifically, we first train a spatial-temporal text detector for localizing text regions in the sequential frames. Secondly, a well-designed text tracker is trained for grouping the localized text regions into corresponding cropped text streams. To efficiently spot video text, we recognize each tracked text stream one-time with a text region quality scoring mechanism instead of identifying the cropped text regions one-by-one. Experiments on two public benchmarks demonstrate that our method achieves impressive performance.