ICCV 2017 论文列表

We propose an active 3D mapping method for depth sensors, which allow individual control of depth-measuring rays, such as the newly emerging Solid State Lidars. The method simultaneously (i) learns to reconstruct a dense 3D voxel-map from sparse depth measurements, and (ii) optimizes the reactive control of depth-measuring rays. To make the first step towards the online control optimization, we propose a fast greedy algorithm, which needs to update its cost function in only a small fraction of possible rays. The approximation ratio of the greedy algorithm is derived. Experimental evaluation on the subset of the Kitti dataset demonstrates significant improvement in the 3D map accuracy when learning-to-reconstruct from sparse measurements is coupled with the optimization where-to-measure.

This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal features in a video sequence respectively, while the memory module captures the evolution of objects over time. The module to build a 'visual memory' in video, i.e., a joint representation of all the video frames, is realized with a convolutional recurrent unit learned from a small number of training video sequences. Given a video frame as input, our approach assigns each pixel an object or background label based on the learned spatio-temporal features as well as the 'visual memory' specific to the video, acquired automatically without any manually-annotated frames. We evaluate our method extensively on two benchmarks, DAVIS and Freiburg-Berkeley motion segmentation datasets, and show state-of-the-art results. For example, our approach outperforms the top method on the DAVIS dataset by nearly 6%. We also provide an extensive ablative analysis to investigate the influence of each component in the proposed framework.

Recognizing fine-grained categories (e.g., bird species) highly relies on discriminative part localization and part-based fine-grained feature learning. Existing approaches predominantly solve these challenges independently, while neglecting the fact that part localization (e.g., head of a bird) and fine-grained feature learning (e.g., head shape) are mutually correlated. In this paper, we propose a novel part learning approach by a multi-attention convolutional neural network (MA-CNN), where part generation and feature learning can reinforce each other. MA-CNN consists of convolution, channel grouping and part classification sub-networks. The channel grouping network takes as input feature channels from convolutional layers, and generates multiple parts by clustering, weighting and pooling from spatially-correlated channels. The part classification network further classifies an image by each individual part, through which more discriminative fine-grained features can be learned. Two losses are proposed to guide the multi-task learning of channel grouping and part classification, which encourages MA-CNN to generate more discriminative parts from feature channels and learn better fine-grained features from parts in a mutual reinforced way. MA-CNN does not need bounding box/part annotation and can be trained end-to-end. We incorporate the learned parts from MA-CNN with part-CNN for recognition, and show the best performances on three challenging published fine-grained datasets, e.g., CUB-Birds, FGVC-Aircraft and Stanford-Cars.

Outdoor lighting has extremely high dynamic range. This makes the process of capturing outdoor environment maps notoriously challenging since special equipment must be used. In this work, we propose an alternative approach. We first capture lighting with a regular, LDR omnidirectional camera, and aim to recover the HDR after the fact via a novel, learning-based inverse tonemapping method. We propose a deep autoencoder framework which regresses linear, high dynamic range data from non-linear, saturated, low dynamic range panoramas. We validate our method through a wide set of experiments on synthetic data, as well as on a novel dataset of real photographs with ground truth. Our approach finds applications in a variety of settings, ranging from outdoor light capture to image matching.

We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative `image guessing' game between two agents -- Qbot and Abot -- who communicate in natural language dialog so that Qbot can select an unseen image from a lineup of images. We use deep reinforcement learning (RL) to end-to-end learn the policies of these agents -- from pixels to multi-agent multi-round dialog to game reward. We demonstrate two experimental results. First, as a `sanity check' demonstration of pure RL (from scratch), we show results on a synthetic world, where the agents communicate in ungrounded vocabulary, ie, symbols with no pre-specified meanings (X, Y, Z). We find that two bots invent their own communication protocol and start using certain symbols to ask/answer about certain visual attributes (shape/color/size). Thus, we demonstrate the emergence of grounded language and communication among `visual' dialog agents with no human supervision at all. Second, we conduct large-scale real-image experiments on the VisDial dataset, where we pretrain on dialog data and show that the RL fine-tuned agents significantly outperform supervised pretraining. Interestingly, the RL Qbot learns to ask questions that Abot is good at, ultimately resulting in more informative dialog and a better team.

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing 3D shapes; and a 3D shape completion network that can extract the full shape of an object from partial observations. We also demonstrate the benefits of configuring networks to perform probabilistic predictions as well as of geometry-aware data augmentation schemes. We obtain state-of-the-art results on publicly-available benchmarks.

Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes. As a result, these black-box models often learn to exploit biases in the data rather than learning to perform visual reasoning. Inspired by module networks, this paper proposes a model for visual reasoning that consists of a program generator that constructs an explicit representation of the reasoning process to be performed, and an execution engine that executes the resulting program to produce an answer. Both the program generator and the execution engine are implemented by neural networks, and are trained using a combination of backpropagation and REINFORCE. Using the CLEVR benchmark for visual reasoning, we show that our model significantly outperforms strong baselines and generalizes better in a variety of settings.

Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications. Perspective-n-Point (PnP) solvers are routinely used for camera pose estimation, provided that a good quality set of 2D-3D feature correspondences are known beforehand. However, finding optimal correspondences between 2D key-points and a 3D point-set is non-trivial, especially when only geometric (position) information is known. Existing approaches to the simultaneous pose and correspondence problem use local optimisation, and are therefore unlikely to find the optimal solution without a good pose initialisation, or introduce restrictive assumptions. Since a large proportion of outliers are common for this problem, we instead propose a globally-optimal inlier set cardinality maximisation approach which jointly estimates optimal camera pose and optimal correspondences. Our approach employs branch-and-bound to search the 6D space of camera poses, guaranteeing global optimality without requiring a pose prior. The geometry of SE(3) is used to find novel upper and lower bounds for the number of inliers and local optimisation is integrated to accelerate convergence. The evaluation empirically supports the optimality proof and shows that the method performs much more robustly than existing approaches, including on a large-scale outdoor data-set.

Parsing urban scene images is critical for self-driving. Most of current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet "undoes" the camera perspective projection--analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRF model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance.

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors.

We address the problem of incrementally modeling and forecasting long-term goals of a first-person camera wearer: what the user will do, where they will go, and what goal they seek. In contrast to prior work in trajectory forecasting, our algorithm, Darko, goes further to reason about semantic states (will I pick up an object?), and future goal states that are far both in terms of space and time. Darko learns and forecasts from first-person visual observations of the user's daily behaviors via an Online Inverse Reinforcement Learning (IRL) approach. Classical IRL discovers only the rewards in a batch setting, whereas Darko discovers the states, transitions, rewards, and goals of a user from streaming data. Among other results, we show Darko forecasts goals better than competing methods in both noisy and ideal settings, and our approach is theoretically and empirically no-regret.

As a postprocessing procedure, diffusion process has demonstrated its ability of substantially improving the performance of various visual retrieval systems. Whereas, great efforts are also devoted to similarity (or metric) fusion, seeing that only one individual type of similarity cannot fully reveal the intrinsic relationship between objects. This stimulates a great research interest of considering similarity fusion in the framework of diffusion process (i.e., fusion with diffusion) for robust retrieval. In this paper, we firstly revisit representative methods about fusion with diffusion, and provide new insights which are ignored by previous researchers. Then, observing that existing algorithms are susceptible to noisy similarities, the proposed Regularized Ensemble Diffusion (RED) is bundled with an automatic weight learning paradigm, so that the negative impacts of noisy similarities are suppressed. At last, we integrate several recently-proposed similarities with the proposed framework. The experimental results suggest that we can achieve new state-of-the-art performances on various retrieval tasks, including 3D shape retrieval on ModelNet dataset, and image retrieval on Holidays and Ukbench dataset.

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics tend to produce over-smoothed images that lack high-frequency textures and do not look natural despite yielding high PSNR values. We propose a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixel-accurate reproduction of ground truth images during training. By using feed-forward fully convolutional neural networks in an adversarial training setting, we achieve a significant boost in image quality at high magnification ratios. Extensive experiments on a number of datasets show the effectiveness of our approach, yielding state-of-the-art results in both quantitative and qualitative benchmarks.

The increasing scale of Structure-from-Motion is fundamentally limited by the conventional optimization framework for the all-in-one global bundle adjustment. In this paper, we propose a distributed approach to coping with this global bundle adjustment for very large scale Structure-from-Motion computation. First, we derive the distributed formulation from the classical optimization algorithm ADMM, Alternating Direction Method of Multipliers, based on the global camera consensus. Then, we analyze the conditions under which the convergence of this distributed optimization would be guaranteed. In particular, we adopt over-relaxation and self-adaption schemes to improve the convergence rate. After that, we propose to split the large scale camera-point visibility graph in order to reduce the communication overheads of the distributed computing. The experiments on both public large scale SfM data-sets and our very large scale aerial photo sets demonstrate that the proposed distributed method clearly outperforms the state-of-the-art method in efficiency and accuracy.

Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a 'sub-pixel motion compensation' (SPMC) layer in a CNN framework. Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, scalable CNN framework effectively incorporates the SPMC layer and fuses multiple frames to reveal image details. Our implementation can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the effectiveness of our approach on sophisticated vision tasks of object detection and semantic segmentation. The code would be released.

Image clustering is a crucial but challenging task in machine learning and computer vision. Existing methods often ignore the combination between feature learning and clustering. To tackle this problem, we propose Deep Adaptive Clustering (DAC) that recasts the clustering problem into a binary pairwise-classification framework to judge whether pairs of images belong to the same clusters. In DAC, the similarities are calculated as the cosine distance between label features of images which are generated by a deep convolutional network (ConvNet). By introducing a constraint into DAC, the learned label features tend to be one-hot vectors that can be utilized for clustering images. The main challenge is that the ground-truth similarities are unknown in image clustering. We handle this issue by presenting an alternating iterative Adaptive Learning algorithm where each iteration alternately selects labeled samples and trains the ConvNet. Conclusively, images are automatically clustered based on the label features. Experimental results show that DAC achieves state-of-the-art performance on five popular datasets, e.g., yielding 97.75% clustering accuracy on MNIST, 52.18% on CIFAR-10 and 46.99% on STL-10.

Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization. In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor. Experimental results show that this model outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks.

Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our analysis, we propose a novel hierarchical, parallel and multi-scale residual architecture that yields large performance improvement over the standard bottleneck block while having the same number of parameters, thus bridging the gap between the original network and its binarized counterpart. (c) We perform a large number of ablation studies that shed light on the properties and the performance of the proposed block. (d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance. Code can be downloaded from https://www.adrianbulat.com/binary-cnn-landmarks