In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is able to discover highly competitive architectures for generally better image generation results with a considerably reduced computational burden: 7 GPU hours. Our code is available at https://github.com/Yuantian013/E2GAN.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this paper, we propose a novel approach, called AR-Net (Adaptive Resolution Network), that selects on-the-fly the optimal resolution for each frame conditioned on the input for efficient action recognition in long untrimmed videos. Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency. We efficiently train the policy network jointly with the recognition model using standard back-propagation. Extensive experiments on several challenging action recognition benchmark datasets well demonstrate the efficacy of our proposed approach over state-of-the-art methods. The project page can be found at https://mengyuest.github.io/AR-Net
Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The domain similarity between those domains is critical for domain adaptation performance. To describe and learn relations between different domains, we propose a novel Domain2Vec model to provide vectorial representations of visual domains based on joint learning of feature disentanglement and Gram matrix. To evaluate the effectiveness of our Domain2Vec model, we create two large-scale cross-domain benchmarks. The first one is TinyDA, which contains 54 domains and about one million MNIST-style images. The second benchmark is DomainBank, which is collected from 56 existing vision datasets. We demonstrate that our embedding is capable of predicting domain similarities that match our intuition about visual relations between different domains. Extensive experiments are conducted to demonstrate the power of our new datasets in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model.
In this paper, we present a Haze-Aware Representation Distillation Generative Adversarial Network named HardGAN for single-image dehazing. Unlike previous studies that intend to model the transmission map and global atmospheric light jointly to restore a clear image, we solve this regression problem by a multi-scale structure neural network embedded with our proposed Haze-Aware Representation Distillation (HARD) layer. Moreover, we re-introduce to utilize the normalization layer skillfully instead of stacking with the convolution layer directly as before to avoid the useful information wash away, as claimed in many image quality enhancement studies. Extensive experiment on several synthetic benchmark datasets as well as the NTIRE 2020 real-world images show our proposed multi-layer GAN-based network with HARD performs favorably against the state-of-the-art methods in terms of PSNR, SSIM, LPIPS, and human subjective evaluation.
Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks are computationally too expensive to be directly applied on mobile devices. In this work, we propose a light-weight, efficient neural network-based raw image denoiser that runs smoothly on mainstream mobile devices, and produces high quality denoising results. Our key insights are twofold:(1) by measuring and estimating sensor noise level, a smaller network trained on synthetic sensor-specific data can out-perform larger ones trained on general data;(2) the large noise level variation under different ISO settings can be removed by a novel k-Sigma Transform, allowing a small network to efficiently handle a wide range of noise levels. We conduct extensive experiments to demonstrate the efficiency and accuracy of our approach. Our proposed mobile-friendly denoising model runs at ~70 milliseconds per megapixel on Qualcomm Snapdragon 855 chipset, and it is the basis of the night shot feature of several flagship smartphones released in 2019.
While existing works have explored a variety of techniques to push the envelop of weakly-supervised semantic segmentation, there is still a significant gap compared to the supervised methods. In real-world application, besides massive amount of weakly-supervised data there are usually a few available pixel-level annotations, based on which semi-supervised track becomes a promising way for semantic segmentation. Current methods simply bundle these two different sets of annotations together to train a segmentation network. However, we discover that such treatment is problematic and achieves even worse results than just using strong labels, which indicates the misuse of the weak ones. To fully explore the potential of the weak labels, we propose to impose separate treatments of strong and weak annotations via a strong-weak dual-branch network, which discriminates the massive inaccurate weak supervisions from those strong ones. We design a shared network component to exploit the joint discrimination of strong and weak annotations; meanwhile, the proposed dual branches separately handle full and weak supervised learning and effectively eliminate their mutual interference. This simple architecture requires only slight additional computational costs during training yet brings significant improvements over the previous methods. Experiments on two standard benchmark datasets show the effectiveness of the proposed method.
Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant gap towards describing the overall content of a video. We fill this gap by presenting a large-scale ``Holistic Video Understanding Dataset""~(HVU). HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene. HVU contains approx.~572k videos in total with 9 million annotations for training, validation, and test set spanning over 3142 labels. HVU encompasses semantic aspects defined on categories of scenes, objects, actions, events, attributes, and concepts which naturally capture the real-world scenarios.We demonstrate the generalisation capability of HVU on three challenging tasks: 1.) Video classification, 2.) Video captioning and 3.) Video clustering tasks. In particular for video classification, we introduce a new spatio-temporal deep neural network architecture called ``Holistic Appearance and Temporal Network""~(HATNet) that builds on fusing 2D and 3D architectures into one by combining intermediate representations of appearance and temporal cues. HATNet focuses on the multi-label and multi-task learning problem and is trained in an end-to-end manner. %The experiments show that HATNet trained on HVU outperforms current state-of-the-art methods on challenging human action datasets: HMDB51, UCF101, and Kinetics. The dataset and codes will be made publicly available. Via our experiments, we validate the idea that holistic representation learning is complementary, and can play a key role in enabling many real-world applications.
We address character grounding and re-identification in multiple story-based videos like movies and associated text descriptions. In order to solve these related tasks in a mutually rewarding way, we propose a model named Character in Story Identification Network (CiSIN). Our method builds two semantically informative representations via joint training of multiple objectives for character grounding, video/text re-identification and gender prediction: Visual Track Embedding from videos and Textual Character Embedding from text context. These two representations are learned to retain rich semantic multimodal information that enables even simple MLPs to achieve the state-of-the-art performance on the target tasks. More specifically, our CiSIN model achieves the best performance in the Fill-in the Characters task of LSMDC 2019 challenges. Moreover, it outperforms previous state-of-the-art models in M-VAD Names dataset as a benchmark of multimodal character grounding and re-identification.
Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes — from 1 example per class to 1 M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.
For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce a similarly diverse dataset for Tracking Any Object (TAO). It consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. Importantly, we adopt a bottom-up approach for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets. To ensure scalability of annotation, we employ a federated approach that focuses manual effort on labeling tracks for those relevant objects in a video (e.g., those that move). We perform an extensive evaluation of state-of-the-art trackers and make a number of important discoveries regarding large-vocabulary tracking in an open-world. In particular, we show that existing single- and multi-object trackers struggle when applied to this scenario in the wild, and that detection-based, multi-object trackers are in fact competitive with user-initialized ones. We hope that our dataset and analysis will boost further progress in the tracking community.
Visual saliency modeling for images and videos is treated as two independent tasks in recent computer vision literature. While image saliency modeling is a well-studied problem and progress on benchmarks like SALICON and MIT300 is slowing, video saliency models have shown rapid gains on the recent DHF1K benchmark. Here, we take a step back and ask: Can image and video saliency modeling be approached via a unified model, with mutual benefit? We identify different sources of domain shift between image and video saliency data and between different video saliency datasets as a key challenge for effective joint modelling. To address this we propose four novel domain adaptation techniques - Domain-Adaptive Priors, Domain-Adaptive Fusion, Domain-Adaptive Smoothing and Bypass-RNN - in addition to an improved formulation of learned Gaussian priors. We integrate these techniques into a simple and lightweight encoder-RNN-decoder-style network, UNISAL, and train it jointly with image and video saliency data. We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300. With one set of parameters, UNISAL achieves state-of-the-art performance on all video saliency datasets and is on par with the state-of-the-art for image saliency datasets, despite faster runtime and a 5 to 20-fold smaller model size compared to all competing deep methods. We provide retrospective analyses and ablation studies which confirm the importance of the domain shift modeling. The code is available at https://github.com/rdroste/unisal.
ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation
PDF ↗Gaze estimation is a fundamental task in many applications of computer vision, human computer interaction and robotics. Many state-of-the-art methods are trained and tested on custom datasets, making comparison across methods challenging. Furthermore, existing gaze estimation datasets have limited head pose and gaze variations, and the evaluations are conducted using different protocols and metrics. In this paper, we propose a new gaze estimation dataset called ETH-XGaze, consisting of over one million high-resolution images of varying gaze under extreme head poses. We collect this dataset from 110 participants with a custom hardware setup including 18 digital SLR cameras and adjustable illumination conditions, and a calibrated system to record ground truth gaze targets. We show that our dataset can significantly improve the robustness of gaze estimation methods across different head poses and gaze angles. Additionally, we define a standardized experimental protocol and evaluation metric on ETH-XGaze, to better unify gaze estimation research going forward. The dataset and benchmark website are available at https://ait.ethz.ch/projects/2020/ETH-XGaze
Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
PDF ↗Motivated by the problem relatedness between unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), many state-of-the-art UDA methods adopt SSL principles (e.g., the cluster assumption) as their learning ingredients. However, they tend to overlook the very domain-shift nature of UDA. In this work, we take a step further to study the proper extensions of SSL techniques for UDA. Taking the algorithm of label propagation (LP) as an example, we analyze the challenges of adopting LP to UDA and theoretically analyze the conditions of affinity graph/matrix construction in order to achieve better propagation of true labels to unlabeled instances. Our analysis suggests a new algorithm of Label Propagation with Augmented Anchors (A$^2$LP), which could potentially improve LP via generation of unlabeled virtual instances (i.e., the augmented anchors) with high-confidence label predictions. To make the proposed A$^2$LP useful for UDA, we propose empirical schemes to generate such virtual instances. The proposed schemes also tackle the domain-shift challenge of UDA by alternating between pseudo labeling via A$^2$LP and domain-invariant feature learning. Experiments show that such a simple SSL extension improves over representative UDA methods of domain-invariant feature learning, and could empower two state-of-the-art methods on benchmark UDA datasets. Our results show the value of further investigation on SSL techniques for UDA problems.
Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet -- a holistic dataset for movie understanding. MovieNet contains 1,100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes and identities, 42K scene boundaries, 2.5K aligned description sentences, 65K tags of place and action, and 92K tags of cinematic style. To the best of our knowledge, MovieNet is the largest dataset with richest annotations for comprehensive movie understanding. Based on MovieNet, we set up several benchmarks for movie understanding from different angles. Extensive experiments are executed on these benchmarks to show the immeasurable value of MovieNet and the gap of current approaches towards comprehensive movie understanding. We believe that such a holistic dataset would promote the researches on story-based long video understanding and beyond. MovieNet will be published in compliance with regulations at https://movienet.github.io.
In this paper, we propose an efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely $D^{2}$HC-RMVSNet, for accurate dense point cloud reconstruction. Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a hybrid HRU-LSTM (Hybrid Recurrent U-LSTM) to regularize 3D matching volume into predicted depth map, which efficiently aggregates different scale information by coupling LSTM and U-Net architecture. To further improve the accuracy and completeness of reconstructed point clouds, we leverage a dynamic consistency checking strategy instead of prefixed parameters and strategies widely adopted in existing methods for dense point cloud reconstruction. In doing so, we dynamically aggregate geometric consistency matching error among all the views. Our method ranks extbf{$1^{st}$} on the complex outdoor extsl{Tanks and Temples} benchmark over all the methods. Extensive experiments on the in-door extsl{DTU} dataset show our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only $19.4\%$ of R-MVSNet memory consumption. The codebase is available at \hyperlink{https://github.com/yhw-yhw/D2HC-RMVSNet}{https://github.com/yhw-yhw/D2HC-RMVSNet}.
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. In this paper, we present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves $67.3\%$ MOTA on the MOT17 challenge at 17 FPS and $89.4\%$ MOTA on the KITTI tracking benchmark at 12 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves $28.3\%$ AMOTA@0.2 on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 22 FPS.
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potential of difficult positive images alongside their sub-regions. The estimated image-to-region similarities can serve as extra training supervision for improving the network in generations, which could in turn gradually refine the fine-grained similarities to achieve optimal performance. Our proposed self-enhanced image-to-region similarity labels effectively deal with the training bottleneck in the state-of-the-art pipelines without any additional parameters or manual annotations in both training and inference. Our method outperforms state-of-the-arts on the standard localization benchmarks by noticeable margins and shows excellent generalization capability on multiple image retrieval datasets.
Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
PDF ↗Automatically generating sentences to describe events and temporally localizing sentences in a video are two important tasks that bridge language and videos. Recent techniques leverage the multimodal nature of videos by using off-the-shelf features to represent videos, but interactions between modalities are rarely explored. Inspired by the fact that there exist cross-modal interactions in the human brain, we propose a novel method for learning pairwise modality interactions in order to better exploit complementary information for each pair of modalities in videos and thus improve performances on both tasks. We model modality interaction in both the sequence and channel levels in a pairwise fashion, and the pairwise interaction also provides some explainability for the predictions of target tasks. We demonstrate the effectiveness of our method and validate specific design choices through extensive ablation studies. Our method turns out to achieve state-of-the-art performances on four standard benchmark datasets: MSVD and MSR-VTT (event captioning task), and Charades-STA and ActivityNet Captions (temporal sentence localization task).
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research. However, existing methods are still hard to be applied in real-world applications due to the requirement of its heavy computation. Model quantization is an effective way to significantly reduce model size and computation time. We propose a simple but effective binary neural networks (BNN) based SISR model with a novel binarization scheme. Specially, we design a bit-accumulation mechanism to approximate the full-precision values, which could realize the approximation to the full precision number by accumulating the multi-layer's one-bit values.The proposed BNN-based SISR method could achieve superior performance with lower computational complexity and less model parameters. Extensive experiments show that the proposed model outperforms the state-of-the-art methods (binarization methods such as BNN, DoReFa-Net and ABC-Net) by large margins on 4 benchmark datasets, specially by average more than 0.8 dB in terms of Peak Signal-to-Noise Ratio (PSNR) on Set5 dataset.
Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, $ extit{i.e.}$ only two face images are available for each ID. $ extit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.