Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabilistic encoder to encode task properties into latent context variables, which then guide CATCH' s controller to quickly ""catch"" top-performing networks. The contexts also assist a network evaluator in filtering inferior candidates and speed up learning. Extensive experiments demonstrate CATCH' s universality and search efficiency over many other widely-recognized algorithms. It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified. This is the first work to our knowledge that proposes an efficient transferrable NAS solution while maintaining robustness across various settings.
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
The general framework for fast universal style transfer consists of an autoencoder and a feature transformation at the bottleneck. We propose a new transformation that iteratively stylizes features with analytical gradient descent. Experiments show this transformation is advantageous in part because it is fast. With control knobs to balance content preservation and style effect transferal, we also show this method can switch between artistic and photo-realistic style transfers and reduce distortion and artifacts. Finally, we show it can be used for applications requiring spatial control and multiple-style transfer.
Accurate and Stable 3D Dense Face Alignment","Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, our model runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. The code and models will be available at \url{https://github.com/cleardusk/3DDFA_V2}.
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed RobustScanner, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios.
In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original search space by dropping unpromising candidates, thus can reduce difficulties for existing NAS methods to find superior architectures. In particular, we propose an angle-based metric to guide the shrinking process. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of child models. We also show that the angle-based metric can converge fast while training supernet, enabling us to get promising shrunk search spaces efficiently. ABS can easily apply to most of NAS approaches (e.g. SPOS, FairNAS, ProxylessNAS, DARTS and PDARTS). Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.
Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view variations are two critical issues. In this work, we propose a novel Siamese denoising autoencoder to learn a 3D pose representation by disentangling the pose-dependent and view-dependent feature from the human skeleton data, in a fully unsupervised manner. These two disentangled features are utilized together as the representation of the 3D pose. To consider both the kinematic and geometric dependencies, a sequential bidirectional recursive network (SeBiReNet) is further proposed to model the human skeleton data. Extensive experiments demonstrate that the learned representation 1) preserves the intrinsic information of human pose, 2) shows good transferability across datasets and tasks. Notably, our approach achieves state-of-the-art performance on two inherently different tasks: pose denoising and unsupervised action recognition. Code and models are available at: https://github.com/NIEQiang001/unsupervised-human-pose.git.
We present a novel physically-motivated deep network for joint shape and material estimation, as well as relighting under novel illumination conditions, using a single image captured by a mobile phone camera. Our physically-based modeling leverages a deep cascaded architecture trained on a large-scale synthetic dataset that consists of complex shapes with microfacet SVBRDF. In contrast to prior works that train rendering layers subsequent to inverse rendering, we propose deep feature sharing and joint training that transfer insights across both tasks, to achieve significant improvements in both reconstruction and relighting. We demonstrate in extensive qualitative and quantitative experiments that our network generalizes very well to real images, achieving high-quality shape and material estimation, as well as image-based relighting. Code, models and data will be publicly released.
While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack and defense mainly rest in single images. In this work, we first attempt to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks. To this end, we take temporal motion into consideration when generating lightweight perturbations over the estimated tracking results frame-by-frame. On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance. On the other hand, we sequentially estimate the perturbations from input sequences and learn to eliminate their effect for performance restoration. We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms. Extensive evaluations on the benchmark datasets demonstrate that the proposed defense method not only eliminates the large performance drops caused by adversarial attacks, but also achieves additional performance gains when deep trackers are not under adversarial attacks.
Prior research has shown that Winograd algorithm can reduce the computational complexity of convolutional neural networks (CNN) with weights and activations represented in floating point. However it is difficult to apply the scheme to the inference of low-precision quantized (e.g. INT8) networks. Our work extends the Winograd algorithm to Residue Number System (RNS). The minimal complexity convolution is computed precisely over large transformation tile (e.g. 10x10 to 16x16) of filters and activation patches using the Winograd transformation and low cost (e.g. 8-bit) arithmetic without degrading the prediction accuracy of the networks during inference. The arithmetic complexity reduction is up to 7.03x while the performance improvement is up to 2.30x to 4.69x. for 3x3 and 5x5 filters respectively.
In augmented reality (AR) or virtual reality (VR) systems, eye tracking is a key technology and requires significant accuracy as well as real-time operation. Many techniques for detecting pupil centers with error range of iris radius have been developed, but few techniques have precise performance with error range of pupil radius. In addition, the conventional methods rarely guarantee real-time pupil center detection in a general-purpose computer environment due to high complexity. Thus, we propose more accurate pupil center detection by improving the representation quality of the network in charge of pupil center detection. This is realized by representation learning based on mutual information. Also, the latency of the entire system is greatly reduced by using non-local block and self-attention block with large receptive field, which makes it accomplish real-time operation. The proposed system not only shows real-time performance of 52 FPS in a general-purpose computer environment but also provides state-of-the-art accuracy in terms of fine level index of 96.71%, 99.84% and 96.38% for BioID, GI4E and Talking Face Video datasets, respectively.
This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns unique representations from the data distribution due to its distinct architecture. This helps the ensemble generalize better by combining every model’s knowledge. The distilled students and ensemble teacher are trained simultaneously without requiring any pretrained weights. Moreover, our proposed method can deliver multi-compressed students with single training, which is efficient and flexible for different scenarios. We provide comprehensive experiments using state-of-the-art classification models to validate our framework’s effectiveness. Notably, using our framework a 97% compressed ResNet110 student model managed to produce a 10.64% relative accuracy gain over its individual baseline training on CIFAR100 dataset. Similarly a 95% compressed DenseNet-BC (k=12) model managed a 8.17% relative accuracy gain.
Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. To address this challenge, we propose an iterative inpainting method with a feedback mechanism. Specifically, we introduce a deep generative model which not only outputs an inpainting result but also a corresponding confidence map. Using this map as feedback, it progressively fills the hole by trusting only high-confidence pixels inside the hole at each iteration and focuses on the remaining pixels in the next iteration. As it reuses partial predictions from the previous iterations as known pixels, this process gradually improves the result. In addition, we propose a guided upsampling network to enable generation of high-resolution inpainting results. We achieve this by extending the Contextual Attention module to borrow high-resolution feature patches in the input image. Furthermore, to mimic real object removal scenarios, we collect a large object mask dataset and synthesize more realistic training data that better simulates user inputs. Experiments show that our method significantly outperforms existing methods in both quantitative and qualitative evaluations.
Multispectral pedestrian detection is capable of adapting to insufficient illumination conditions by leveraging color-thermal modalities. On the other hand, it is still lacking of in-depth insights on how to fuse the two modalities effectively. Compared with traditional pedestrian detection, we find multispectral pedestrian detection suffers from modality imbalance problems which will hinder the optimization process of dual-modality network and depress the performance of detector. Inspired by this observation, we propose Modality Balance Network (MBNet) which facilitates the optimization process in a much more flexible and balanced manner. Firstly, we design a novel Differential Modality Aware Fusion (DMAF) module to make the two modalities complement each other. Secondly, an illumination aware feature alignment module selects complementary features according to the illumination conditions and aligns the two modality features adaptively. Extensive experimental results demonstrate MBNet outperforms the state-of-the-arts on both the challenging KAIST and CVC-14 multispectral pedestrian datasets in terms of the accuracy and the computational efficiency.
Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
PDF ↗Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation. However, further adoption of the joint models are hindered: 1) the diversity of augmentation data is reduced limiting the further enhancement of segmentation, 2) misaligned regions in weakly supervised data disturb the training process, 3) lack of label-based region constraints in few-shot situation limits the registration performance. We propose a novel Deep Complementary Joint Model (DeepRS) for complex scene registration and few-shot segmentation. We embed a perturbation factor in the registration to increase the activity of deformation thus maintaining the augmentation data diversity. We take a pixel-wise discriminator to extract alignment confidence maps which highlight aligned regions in weakly supervised data so the misaligned regions' disturbance will be suppressed via weighting. The outputs from segmentation model are utilized to implement deep-based region constraints thus relieving the label requirements and bringing fine registration. Extensive experiments on the CT dataset of MM-WHS 2017 Challenge show great advantages of our DeepRS that outperforms the existing state-of-the-art models.
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time by randomly sampling classes in meta-training data to construct few-shot tasks for episodic training. While a rich line of work focuses solely on how to extract meta-knowledge across tasks, we exploit the complementary problem on how to generate informative tasks. We argue that the randomly sampled tasks could be sub-optimal and uninformative (e.g., the task of classifying ``dog"" from ``laptop"" is often trivial) to the meta-learner. In this paper, we propose an adaptive task sampling method to improve the generalization performance. Unlike instance based sampling, task based sampling is much more challenging due to the implicit definition of the task in each episode. Therefore, we accordingly propose a greedy class-pair based sampling method, which selects difficult tasks according to class-pair potentials. We evaluate our adaptive task sampling method on two few-shot classification benchmarks, and it achieves consistent improvements across different feature backbones, meta-learning algorithms and datasets.
In this paper, we propose a structural deep metric learning (SDML) method for room layout estimation, which aims to recover the 3D spatial layout of a cluttered indoor scene from a monocular RGB image. Different from existing room layout estimation methods that solve a regression or per-pixel classification problem, we formulate the room layout estimation problem from a metric learning perspective where we explicitly model the structural relations across different images. We propose to learn a latent embedding space where the Euclidean distance can characterize the actual structural difference between the layouts of two rooms. We then minimize the discrepancy between an image and its ground-truth layout in the learned embedding space. We employ a metric model and a layout encoder to map the RGB images and the ground-truth layouts to the embedding space, respectively, and a layout decoder to map the embeddings to the corresponding layouts, where the whole framework is trained in an end-to-end manner. We perform experiments on the widely used Hedau and LSUN datasets and achieve state-of-the-art performance.
Lane detection is a fundamental yet challenging task in autonomous driving and intelligent traffic systems due to perspective projection and occlusion. Most of previous methods utilize semantic segmentation to identify the regions of traffic lanes in an image, and then adopt some curve-fitting method to reconstruct the lanes. In this work, we propose to use polynomial curves to represent traffic lanes and then propose a novel polynomial regression network (PRNet) to directly predict them, where semantic segmentation is not involved. Specifically, PRNet consists of one major branch and two auxiliary branches: (1) polynomial regression to estimate the polynomial coefficients of lanes, (2) initialization classification to detect the initial retrieval point of each lane, and (3) height regression to determine the ending point of each lane. Through the cooperation of three branches, PRNet can detect variable-number of lanes and is highly effective and efficient. We experimentally evaluate the proposed PRNet on two popular benchmark datasets: TuSimple and CULane. The results show that our method significantly outperforms the previous state-of-the-art methods in terms of both accuracy and speed.
As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research on neuroscience reveals that the neurons' ability of modifying their functions dynamically according to context is essential for the perceptual tasks, which has been overlooked in most of CNNs. Motivated by this, we propose one novel Context-Gated Convolution (CGC) to explicitly modify the weights of convolutional layers adaptively under the guidance of global context. As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features. Moreover, our proposed CGC is lightweight and applicable with modern CNN architectures, and consistently improves the performance of CNNs according to extensive experiments on image classification, action recognition, and machine translation. Our code of this paper is available at https://github.com/XudongLinthu/context-gated-convolution.
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data (e.g., semantic maps). Trajectron++ is designed to be tightly integrated with robotic planning and control frameworks; for example, it can produce predictions that are optionally conditioned on ego-agent motion plans. We demonstrate its performance on several challenging real-world trajectory forecasting datasets, outperforming a wide array of state-of-the-art deterministic and generative methods.
Imaging in the dark environment is important for many real-world applications like video surveillance. Recently, the development of Event Cameras raises promising directions in solving this task thanks to its High Dynamic Range (HDR) and low requirement of computational sources. However, such cameras record sparse, asynchronous intensity changes of the scene (called events), instead of canonical images. In this paper, we propose learning to see in the dark by translating the HDR events in low light to canonical sharp images as if captured in day light. Since it is extremely challenging to collect paired event-image training data, a novel unsupervised domain adaptation network is proposed which explicitly separates domain-invariant features (e.g. scene structures) from the domain-specific ones (e.g. detailed textures) to ease representation learning. A detail enhancing branch is proposed to reconstruct day light-specific features from the domain-invariant representations in a residual manner, regularized by a ranking loss. To evaluate the proposed approach, a novel large-scale dataset is captured with a DAVIS240C camera with both day/low light events and intensity images. Experiments on this dataset show that the proposed domain adaptation approach achieves superior performance than various state-of-the-art architectures.