ICCV 2017 Papers

Semantic lines characterize the layout of an image. Despite their importance in image analysis and scene understanding, there is no reliable research for semantic line detection. In this paper, we propose a semantic line detector using a convolutional neural network with multi-task learning, by regarding the line detection as a combination of classification and regression tasks. We use convolution and max-pooling layers to obtain multi-scale feature maps for an input image. Then, we develop the line pooling layer to extract a feature vector for each candidate line from the feature maps. Next, we feed the feature vector into the parallel classification and regression layers. The classification layer decides whether the line candidate is semantic or not. In case of a semantic line, the regression layer determines the offset for refining the line location. Experimental results show that the proposed detector extracts semantic lines accurately and reliably. Moreover, we demonstrate that the proposed detector can be used successfully in three applications: horizon estimation, composition enhancement, and image simplification.

Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains nontrivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images adequately spanning the space of fine-grained visual differences is limited. We propose to overcome the sparsity of supervision problem via synthetically generated images. Building on a state-of-the-art image generation engine, we sample pairs of training images exhibiting slight modifications of individual attributes. Augmenting real training image pairs with these examples, we then train attribute ranking models to predict the relative strength of an attribute in novel pairs of real images. Our results on datasets of faces and fashion images show the great promise of bootstrapping imperfect image generators to counteract sample sparsity for learning to rank.

In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g.intelligent image manipulation. We attempt to accomplish such synthesis: given a source image and a target text description, our model synthesizes images to meet two requirements: 1) being realistic while matching the target text description; 2) maintaining other image features that are irrelevant to the text description. The model should be able to disentangle the semantic information from the two modalities (image and text), and generate new images from the combined semantics. To achieve this, we proposed an end-to-end neural architecture that leverages adversarial learning to automatically learn implicit loss functions, which are optimized to fulfill the aforementioned two requirements. We have evaluated our model by conducting experiments on Caltech-200 bird dataset and Oxford-102 flower dataset, and have demonstrated that our model is capable of synthesizing realistic images that match the given descriptions, while still maintain other features of original images.

Human pose analysis is presently dominated by deep convolutional networks trained with extensive manual annotations of joint locations and beyond. To avoid the need for expensive labeling, we exploit spatiotemporal relations in training videos for self-supervised learning of pose embeddings. The key idea is to combine temporal ordering and spatial placement estimation as auxiliary tasks for learning pose similarities in a Siamese convolutional network. Since the self-supervised sampling of both tasks from natural videos can result in ambiguous and incorrect training labels, our method employs a curriculum learning idea that starts training with the most reliable data samples and gradually increases the difficulty. To further refine the training process we mine repetitive poses in individual videos which provide reliable labels while removing inconsistencies. Our pose embeddings capture visual characteristics of human pose that can boost existing supervised representations in human pose estimation and retrieval. We report quantitative and qualitative results on these tasks in Olympic Sports, Leeds Pose Sports and MPII Human Pose datasets.

The challenge in blind image deblurring is to remove the effects of blur with limited prior information about the nature of the blur process. Existing methods often assume that the blur image is produced by linear convolution with additive Gaussian noise. However, including even a small number of outliers to this model in the kernel estimation process can significantly reduce the resulting image quality. Previous methods mainly rely on some simple but unreliable heuristics to identify outliers for kernel estimation. Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process. The self-paced kernel estimation scheme we propose represents a generalization of existing self-paced learning approaches, in which we gradually detect and include reliable inlier pixel sets in a blurred image for kernel estimation. Moreover, we automatically activate a subset of significant gradients w.r.t. the reliable inlier pixels, and then update the intermediate sharp image and the kernel accordingly. Experiments on both synthetic data and real-world images with various kinds of outliers demonstrate the effectiveness and robustness of the proposed method compared to the state-of-the-art methods.

In this paper we propose a new solution to the text detection problem via border learning. Specifically, we make four major contributions: 1) We analyze the insufficiencies of the classic non-text and text settings for text detection. 2) We introduce the border class to the text detection problem for the first time, and validate that the decoding process is largely simplified with the help of text border. 3) We collect and release a new text detection ppt dataset containing 10,692 images with non-text, border, and text annotations. 4) We develop a lightweight (only 0.28M parameters), fully convolutional network (FCN) to effectively learn borders in text images. The results of our extensive experiments show that the proposed solution achieves comparable performance, and often outperforms state-of-the-art approaches on standard benchmarks--even though our solution only requires minimal post-processing to parse a bounding box from a detected text map, while others often require heavy post-processing.

We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain segmentation information, we set up a CNN to provide an embedding space where region co-membership can be estimated based on Euclidean distance. We use these embeddings to compute a local attention mask relative to every neuron position. We incorporate such masks in CNNs and replace the convolution operation with a "segmentation-aware" variant that allows a neuron to selectively attend to inputs coming from its own region. We call the resulting network a segmentation-aware CNN because it adapts its filters at each image point according to local segmentation cues, while at the same time remaining fully-convolutional. We demonstrate the merit of our method on two widely different dense prediction tasks, that involve classification (semantic segmentation) and regression (optical flow). Our results show that in semantic segmentation we can replace DenseCRF inference with a cascade of segmentation-aware filters, and in optical flow we obtain clearly sharper responses than the ones obtained with comparable networks that do not use segmentation. In both cases segmentation-aware convolution yields systematic improvements over strong baselines.

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The segmentation branch is based on a fully convolutional network, which has been proved effective in image segmentation task, and the optical flow branch takes advantage of the FlowNet model. The unified framework is trained iteratively offline to learn a generic notion, and fine tuned online for specific objects. Extensive experiments on both the video object segmentation and optical flow datasets demonstrate that introducing optical flow improves the performance of segmentation and vice versa, against the state-of-the-art algorithms.

Humans have rich understanding of liquid containers and their contents; for example, we can effortlessly pour water from a pitcher to a cup. Doing so requires estimating the volume of the cup, approximating the amount of water in the pitcher, and predicting the behavior of water when we tilt the pitcher. Very little attention in computer vision has been made to liquids and their containers. In this paper, we study liquid containers and their contents, and propose methods to estimate the volume of containers, approximate the amount of liquid in them, and perform comparative volume estimations all from a single RGB image. Furthermore, we show the results of the proposed model for predicting the behavior of liquids inside containers when one tilts the containers. We also introduce a new dataset of Containers Of liQuid contEnt (COQE) that contains more than 5,000 images of 10,000 liquid containers in context labelled with volume, amount of content, bounding box annotation, and corresponding similar 3D CAD models.

We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection. It also provides perfect camera poses and depth data, allowing investigation into geometric computer vision problems such as optical flow, camera pose estimation, and 3D scene labelling tasks. Random sampling permits virtually unlimited scene configurations, and here we provide 5M rendered RGB-D images from 16K randomly generated 3D trajectories in synthetic layouts, with random but physically simulated object configurations. We compare the semantic segmentation performance of network weights produced from pre-training on RGB images from our dataset against generic VGG-16 ImageNet weights. After fine-tuning on the SUN RGB-D and NYUv2 real-world datasets we find in both cases that the synthetically pre-trained network outperforms the VGG-16 weights. When synthetic pre-training includes a depth channel (something ImageNet cannot natively provide) the performance is greater still. This suggests that large-scale high-quality synthetic RGB datasets with task-specific labels can be more useful for pre-training than real-world generic pre-training such as ImageNet. We host the dataset at http://robotvault.bitbucket.io/scenenet-rgbd.html

We present a scene parsing method that utilizes global context information based on both the parametric and non-parametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and spatial priors for explicit classes inference. We then design modules to embed the feature representations and the priors into the segmentation network as additional global context cues. We show that the proposed method can eliminate false positives that are not compatible with the global context representations. Experiments on both the MIT ADE20K and PASCAL Context datasets show that the proposed method performs favorably against existing methods.

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision tasks jointly in an end-to-end manner. Object, phrase, and caption regions are first aligned with a dynamic graph based on their spatial and semantic connections. Then a feature refining structure is used to pass messages across the three levels of semantic tasks through the graph. We benchmark the learned model on three tasks, and show the joint learning across three tasks with our proposed method can bring mutual improvements over previous models. Particularly, on the scene graph generation task, our proposed method outperforms the state-of-art method with more than 3% margin.

Spectral signatures of natural scenes were earlier found to be distinctive for different scene types with varying spatial envelope properties such as openness, naturalness, ruggedness, and symmetry. Recently, such handcrafted features have been outclassed by deep learning based representations. This paper proposes a novel spectral description of convolution features, implemented efficiently as a unitary transformation within deep network architectures. To the best of our knowledge, this is the first attempt to use deep learning based spectral features explicitly for image classification task. We show that the spectral transformation decorrelates convolutional activations, which reduces co-adaptation between feature detections, thus acts as an effective regularizer. Our approach achieves significant improvements on three large-scale scene-centric datasets (MIT-67, SUN-397, and Places-205). Furthermore, we evaluated the proposed approach on the attribute detection task where its superior performance manifests its relevance to semantically meaningful characteristics of natural scenes.

We use the scattering network as a generic and fixed initialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providing the best results to-date with pre-defined representations while being competitive with Deep CNNs. Using a shallow cascade of 1x1 convolutions, which encodes scattering coefficients that correspond to spatial windows of very small sizes, permits to obtain AlexNet accuracy on the imagenet ILSVRC2012. We demonstrate that this local encoding explicitly learns invariance w.r.t. rotations. Combining scattering networks with a modern ResNet, we achieve a single-crop top 5 error of 11.4% on imagenet ILSVRC2012, comparable to the Resnet-18 architecture, while utilizing only 10 layers. We also find that hybrid architectures can yield excellent performance in the small sample regime, exceeding their end-to-end counterparts, through their ability to incorporate geometrical priors. We demonstrate this on subsets of the CIFAR-10 dataset and on the STL-10 dataset.

Motivated by product detection in supermarkets, this paper studies the problem of object proposal generation in supermarket images and other natural images. We argue that estimation of object scales in images is helpful for generating object proposals, especially for supermarket images where object scales are usually within a small range. Therefore, we propose to estimate object scales of images before generating object proposals. The proposed method for predicting object scales is called ScaleNet. To validate the effectiveness of ScaleNet, we build three supermarket datasets, two of which are real-world datasets used for testing and the other one is a synthetic dataset used for training. In short, we extend the previous state-of-the-art object proposal methods by adding a scale prediction phase. The resulted method outperforms the previous state-of-the-art on the supermarket datasets by a large margin. We also show that the approach works for object proposal on other natural images and it outperforms the previous state-of-the-art object proposal methods on the MS COCO dataset. The supermarket datasets, the virtual supermarkets, and the tools for creating more synthetic datasets will be made public.

Many existing scene parsing methods adopt Convolutional Neural Networks with fixed-size receptive fields, which frequently result in inconsistent predictions of large objects and invisibility of small objects. To tackle this issue, we propose a scale-adaptive convolution to acquire flexible-size receptive fields during scene parsing. Through adding a new scale regression layer, we can dynamically infer the position-adaptive scale coefficients which are adopted to resize the convolutional patches. Consequently, the receptive fields can be adjusted automatically according to the various sizes of the objects in scene images. Thus, the problems of invisible small objects and inconsistent large-object predictions can be alleviated. Furthermore, our proposed scale-adaptive convolutions are not only differentiable to learn the convolutional parameters and scale coefficients in an end-to-end way, but also of high parallelizability for the convenience of GPU implementation. Additionally, since the new scale regression layers are learned implicitly, any extra training supervision of object sizes is unnecessary. Extensive experiments on Cityscapes and ADE20K datasets well demonstrate the effectiveness of the proposed scale-adaptive convolutions.

Scale recovery is one of the central problems for monocular visual odometry. Normally, road plane and camera height are specified as reference to recover the scale. The performances of these methods depend on the plane recognition and height measurement of camera. In this work, we propose a novel method to recover the scale by incorporating the depths estimated from images using deep convolutional neural fields. Our method considers the whole environmental structure as reference rather than a specified plane. The accuracy of depth estimation contributes to the scale recovery. We improve the performance of depth estimation by considering two consecutive frames and egomotion of camera into our networks. The depth refinement and scale recovery are obtained iteratively. In this way, our method can eliminate the scale drift and improve the depth estimation simultaneously. The effectiveness of our method is verified on the KITTI dataset for both visual odometry and depth estimation tasks.

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that selecting training examples plays an equally important role. We propose distance weighted sampling, which selects more informative and stable examples than traditional approaches. In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions. We evaluate our approach on the CUB200-2011, CAR196, and the Stanford Online Products datasets for image retrieval and clustering, and on the LFW dataset for face verification. Our method achieves state-of-the-art performance on all of them.

In this paper we propose a new salient object detection method via structured label prediction. By learning appearance features in rectangular regions, our structural region representation encodes the local saliency distribution with a matrix of binary labels. We show that the linear combination of structured labels can well model the saliency distribution in local regions. Representing region saliency with structured labels has two advantages: 1) it connects the label assignment of all enclosed pixels, which produces a smooth saliency prediction; and 2) regular-shaped nature of structured labels enables well definition of traditional cues such as regional properties and center surround contrast, and these cues help to build meaningful and informative saliency measures. To measure the consistency between a structured label and the corresponding saliency distribution, we further propose an adaptive label ranking algorithm using proposals that are generated by a CNN model. Finally, we introduce a K-NN enhanced graph representation for saliency propagation, which is more favorable for our task than the widely-used adjacent-graph-based ones. Experimental results demonstrate the effectiveness of our proposed method on six popular benchmarks compared with state-of-the-art approaches.