This paper introduces a new activation checkpointing method which allows to significantly decrease memory usage when training Deep Neural Networks with the back-propagation algorithm. Similarly to checkpoint-ing techniques coming from the literature on Automatic Differentiation, it consists in dynamically selecting the forward activations that are saved during the training phase, and then automatically recomputing missing activations from those previously recorded. We propose an original computation model that combines two types of activation savings: either only storing the layer inputs, or recording the complete history of operations that produced the outputs (this uses more memory, but requires fewer recomputations in the backward phase), and we provide an algorithm to compute the optimal computation sequence for this model. This paper also describes a PyTorch implementation that processes the entire chain, dealing with any sequential DNN whose internal layers may be arbitrarily complex and automatically executing it according to the optimal checkpointing strategy computed given a memory limit. Through extensive experiments, we show that our implementation consistently outperforms existing checkpoint-ing approaches for a large class of networks, image sizes and batch sizes.
We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects. The proposed model demonstrates super-realtime inference speed on mobile GPUs (100-1000+ FPS, depending on the device and model variant) and a high prediction quality that is comparable to the variance in manual annotations of the same image.
Recent advances show that Neural Architectural Search (NAS) method is able to find state-of-the-art image classification deep architectures. In this paper, we consider the one-shot NAS problem for resource constrained applications. This problem is of great interest because it is critical to choose different architectures according to task complexity when the resource is constrained. Previous techniques are either too slow for one-shot learning or does not take the resource constraint into consideration. In this paper, we propose the resource constrained differentiable architecture search (RC-DARTS) method to learn architectures that are significantly smaller and faster while achieving comparable accuracy. Specifically, we propose to formulate the RC-DARTS task as a constrained optimization problem by adding the resource constraint. An iterative projection method is proposed to solve the given constrained optimization problem. We also propose a multi-level search strategy to enable layers at different depths to adaptively learn different types of neural architectures. Through extensive experiments on the Cifar10 and ImageNet datasets, we show that the RC-DARTS method learns lightweight neural architectures which have smaller model size and lower computational complexity while achieving comparable or better performances than the state-of-the-art methods.
Numerical methods for solving linear eigenvalue problem are widely studiedand used in science and engineering. In this paper, we propose a generalizednumerical method for solving eigenproblems for generic, nonlinear opera-tors. This has potentially wide implications, since most image processingalgorithms (e.g. denoising) can be viewed as nonlinear operators, whoseeigenproblem analysis provides information on the most- and least-suitablefunctions as input. We solve the problem by a nonlinear adaptation of thepower method, a well known linear eigensolver. An analysis and valida-tion framework is proposed, as well as preliminary theory. We validate themethod using total-variation (TV) and demonstrate it on the EPLL denoiser(Zoran-Weiss). Finally, we suggest an encryption-decryption application.
Due to its potential wide applications in video surveillance and other computer vision tasks like tracking, person re-identification (ReID) has become popular and been widely investigated. However, conventional person re-identification can only handle RGB color images, which will fail at dark conditions. Thus RGB-infrared ReID (also known as Infrared-Visible ReID or Visible-Thermal ReID) is proposed. Apart from appearance discrepancy in traditional ReID caused by illumination, pose variations and viewpoint changes, modality discrepancy produced by cameras of the different spectrum also exists, which makes RGB-infrared ReID more difficult. To address this problem, we focus on extracting the shared cross-spectrum features of different modalities. In this paper, a novel multi-spectrum image generation method is proposed and the generated samples are utilized to help the network to find discriminative information for re-identifying the same person across modalities. Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem. Combining those two parts together, we also design a one-stream neural network combining the aforementioned methods to extract compact representations of person images, called Cross-spectrum Dual-subspace Pairing (CDP) model. Furthermore, during the training process, we also propose a Dynamic Hard Spectrum Mining method to automatically mine more hard samples from hard spectrum based on the current model state to further boost the performance. Extensive experimental results on two public datasets, SYSU-MM01 with RGB + near-infrared images and RegDB with RGB + far-infrared images, have demonstrated the efficiency and generality of our proposed method.
Recent years have seen a dramatic expansion of tasks and datasets posed as question answering, from reading comprehension, semantic role labeling, and even machine translation, to image and video understanding. With this expansion, there are many differing views on the utility and definition of "question answering" itself. Some argue that its scope should be narrow, or broad, or that it is overused in datasets today. In this opinion piece, we argue that question answering should be considered a format which is sometimes useful for studying particular phenomena, not a phenomenon or task in itself. We discuss when a task is correctly described as question answering, and when a task is usefully posed as question answering, instead of using some other format.
Sunspots, as seen in white light or continuum images, are associated with regions of high magnetic activity on the Sun, visible on magnetogram images. Their complexity is correlated with explosive solar activity and so classifying these active regions is useful for predicting future solar activity. Current classification of sunspot groups is visually based and suffers from bias. Supervised learning methods can reduce human bias but fail to optimally capitalize on the information present in sunspot images. This paper uses two image modalities (continuum and magnetogram) to characterize the spatial and modal interactions of sunspot and magnetic active region images and presents a new approach to cluster the images. Specifically, in the framework of image patch analysis, we estimate the number of intrinsic parameters required to describe the spatial and modal dependencies, the correlation between the two modalities and the corresponding spatial patterns, and examine the phenomena at different scales within the images. To do this, we use linear and nonlinear intrinsic dimension estimators, canonical correlation analysis, and multiresolution analysis of intrinsic dimension.
Most gradient-based approaches to meta-learning do not explicitly account for the fact that different parts of the underlying model adapt by different amounts when applied to a new task. For example, the input layers of an image classification convnet typically adapt very little, while the output layers can change significantly. This can cause parts of the model to begin to overfit while others underfit. To address this, we introduce a hierarchical Bayesian model with per-module shrinkage parameters, which we propose to learn by maximizing an approximation of the predictive likelihood using implicit differentiation. Our algorithm subsumes Reptile and outperforms variants of MAML on two synthetic few-shot meta-learning problems.
This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the body motion, face expression, and pose of the person in source video. We use upper body keypoints, facial action units and poses as intermediate representations between source video and target video. Instead of directly transferring the source video to the target video, we firstly map the source person's facial action units and poses into the target person's facial landmarks, then combine the normalized upper body keypoints and generated facial landmarks with spatio-temporal smoothing to generate the corresponding target video's image. Experimental results demonstrated the effectiveness of our method.
We show how we can globally edit images using textual instructions: given a source image and a textual instruction for the edit, generate a new image transformed under this instruction. To tackle this novel problem, we develop three different trainable models based on RNN and Generative Adversarial Network (GAN). The models (bucket, filter bank, and end-to-end) differ in how much expert knowledge is encoded, with the most general version being purely end-to-end. To train these systems, we use Amazon Mechanical Turk to collect textual descriptions for around 2000 image pairs sampled from several datasets. Experimental results evaluated on our dataset validate our approaches. In addition, given that the filter bank model is a good compromise between generality and performance, we investigate it further by replacing RNN with Graph RNN, and show that Graph RNN improves performance. To the best of our knowledge, this is the first computational photography work on global image editing that is purely based on free-form textual instructions.