Parsing urban scene images benefits many applications, especially self-driving. Most of the 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 CRFs 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.
This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an $l$-layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rate of $\mathcal{O}(r^{2l}\sqrt{d\log(l)}/\sqrt{n})$ with training sample size of $n$, the total weight dimension of $d$ and the magnitude bound $r$ of weight of each layer. We then derive the stability and generalization bounds for the empirical risk based on this result. Besides, we establish the uniform convergence of gradient of the empirical risk to its population counterpart. We prove the one-to-one correspondence of the non-degenerate stationary points between the empirical and population risks with convergence guarantees, which describes the landscape of deep neural networks. In addition, we analyze these properties for deep nonlinear neural networks with sigmoid activation functions. We prove similar results for convergence behavior of their empirical risks as well as the gradients and analyze properties of their non-degenerate stationary points. To our best knowledge, this work is the first one theoretically characterizing landscapes of deep learning algorithms. Besides, our results provide the sample complexity of training a good deep neural network. We also provide theoretical understanding on how the neural network depth $l$, the layer width, the network size $d$ and parameter magnitude determine the neural network landscapes.
Visual question answering as recently proposed multimodal learning task has enjoyed wide attention from the deep learning community. Lately, the focus was on developing new representation fusion methods and attention mechanisms to achieve superior performance. On the other hand, very little focus has been put on the models' loss function, arguably one of the most important aspects of training deep learning models. The prevailing practice is to use cross entropy loss function that penalizes the probability given to all the answers in the vocabulary except the single most common answer for the particular question. However, the VQA evaluation function compares the predicted answer with all the ground-truth answers for the given question and if there is a matching, a partial point is given. This causes a discrepancy between the model's cross entropy loss and the model's accuracy as calculated by the VQA evaluation function. In this work, we propose a novel loss, termed as soft cross entropy, that considers all ground-truth answers and thus reduces the loss-accuracy discrepancy. The proposed loss leads to an improved training convergence of VQA models and an increase in accuracy as much as 1.6%.
In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. To enjoy the benefits from both path topologies, our proposed Dual Path Network shares common features while maintaining the flexibility to explore new features through dual path architectures. Extensive experiments on three benchmark datasets, ImagNet-1k, Places365 and PASCAL VOC, clearly demonstrate superior performance of the proposed DPN over state-of-the-arts. In particular, on the ImagNet-1k dataset, a shallow DPN surpasses the best ResNeXt-101(64x4d) with 26% smaller model size, 25% less computational cost and 8% lower memory consumption, and a deeper DPN (DPN-131) further pushes the state-of-the-art single model performance with about 2 times faster training speed. Experiments on the Places365 large-scale scene dataset, PASCAL VOC detection dataset, and PASCAL VOC segmentation dataset also demonstrate its consistently better performance than DenseNet, ResNet and the latest ResNeXt model over various applications.
We investigate the problem of person search in the wild in this work. Instead of comparing the query against all candidate regions generated in a query-blind manner, we propose to recursively shrink the search area from the whole image till achieving precise localization of the target person, by fully exploiting information from the query and contextual cues in every recursive search step. We develop the Neural Person Search Machines (NPSM) to implement such recursive localization for person search. Benefiting from its neural search mechanism, NPSM is able to selectively shrink its focus from a loose region to a tighter one containing the target automatically. In this process, NPSM employs an internal primitive memory component to memorize the query representation which modulates the attention and augments its robustness to other distracting regions. Evaluations on two benchmark datasets, CUHK-SYSU Person Search dataset and PRW dataset, have demonstrated that our method can outperform current state-of-the-arts in both mAP and top-1 evaluation protocols.
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple scales. However, the performance gain of such ad hoc architectures is usually limited to pay off the computational cost. In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to "super-resolved" ones, achieving similar characteristics as large objects and thus more discriminative for detection. For this purpose, we propose a new Perceptual Generative Adversarial Network (Perceptual GAN) model that improves small object detection through narrowing representation difference of small objects from the large ones. Specifically, its generator learns to transfer perceived poor representations of the small objects to super-resolved ones that are similar enough to real large objects to fool a competing discriminator. Meanwhile its discriminator competes with the generator to identify the generated representation and imposes an additional perceptual requirement - generated representations of small objects must be beneficial for detection purpose - on the generator. Extensive evaluations on the challenging Tsinghua-Tencent 100K and the Caltech benchmark well demonstrate the superiority of Perceptual GAN in detecting small objects, including traffic signs and pedestrians, over well-established state-of-the-arts.
Video based person re-identification plays a central role in realistic security and video surveillance. In this paper we propose a novel Accumulative Motion Context (AMOC) network for addressing this important problem, which effectively exploits the long-range motion context for robustly identifying the same person under challenging conditions. Given a video sequence of the same or different persons, the proposed AMOC network jointly learns appearance representation and motion context from a collection of adjacent frames using a two-stream convolutional architecture. Then AMOC accumulates clues from motion context by recurrent aggregation, allowing effective information flow among adjacent frames and capturing dynamic gist of the persons. The architecture of AMOC is end-to-end trainable and thus motion context can be adapted to complement appearance clues under unfavorable conditions (e.g. occlusions). Extensive experiments are conduced on three public benchmark datasets, i.e., the iLIDS-VID, PRID-2011 and MARS datasets, to investigate the performance of AMOC. The experimental results demonstrate that the proposed AMOC network outperforms state-of-the-arts for video-based re-identification significantly and confirm the advantage of exploiting long-range motion context for video based person re-identification, validating our motivation evidently.
We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a non-asymptotic convergence analysis of our framework and derive computational and sample complexities for our algorithm to converge to an $\epsilon$-stationary point in expectation. In addition, extensive experiments for a wide class of SMF formulations demonstrate that our framework consistently yields faster convergence and a more accurate output dictionary vis-\`a-vis state-of-the-art frameworks.
Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of an image for better capturing critical difference and demonstrated promising performance. However, without consideration of the diversity in attention process, most of existing attention models perform poorly in classifying fine-grained objects. In this paper, we propose a diversified visual attention network (DVAN) to address the problems of fine-grained object classification, which substan- tially relieves the dependency on strongly-supervised information for learning to localize discriminative regions compared with attentionless models. More importantly, DVAN explicitly pursues the diversity of attention and is able to gather discriminative information to the maximal extent. Multiple attention canvases are generated to extract convolutional features for attention. An LSTM recurrent unit is employed to learn the attentiveness and discrimination of attention canvases. The proposed DVAN has the ability to attend the object from coarse to fine granularity, and a dynamic internal representation for classification is built up by incrementally combining the information from different locations and scales of the image. Extensive experiments con- ducted on CUB-2011, Stanford Dogs and Stanford Cars datasets have demonstrated that the proposed diversified visual attention networks achieve competitive performance compared to the state- of-the-art approaches, without using any prior knowledge, user interaction or external resource in training or testing.
Person search in real-world scenarios is a new challenging computer version task with many meaningful applications. The challenge of this task mainly comes from: (1) unavailable bounding boxes for pedestrians and the model needs to search for the person over the whole gallery images; (2) huge variance of visual appearance of a particular person owing to varying poses, lighting conditions, and occlusions. To address these two critical issues in modern person search applications, we propose a novel Individual Aggregation Network (IAN) that can accurately localize persons by learning to minimize intra-person feature variations. IAN is built upon the state-of-the-art object detection framework, i.e., faster R-CNN, so that high-quality region proposals for pedestrians can be produced in an online manner. In addition, to relieve the negative effect caused by varying visual appearances of the same individual, IAN introduces a novel center loss that can increase the intra-class compactness of feature representations. The engaged center loss encourages persons with the same identity to have similar feature characteristics. Extensive experimental results on two benchmarks, i.e., CUHK-SYSU and PRW, well demonstrate the superiority of the proposed model. In particular, IAN achieves 77.23% mAP and 80.45% top-1 accuracy on CUHK-SYSU, which outperform the state-of-the-art by 1.7% and 1.85%, respectively.