CVPR 2018 Papers

Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attention weights or text-based generation of post-hoc justifications. We propose a multimodal approach to explanation, and argue that the two modalities provide complementary explanatory strengths. We collect two new datasets to define and evaluate this task, and propose a novel model which can provide joint textual rationale generation and attention visualization. Our datasets define visual and textual justifications of a classification decision for activity recognition tasks (ACT-X) and for visual question answering tasks (VQA-X). We quantitatively show that training with the textual explanations not only yields better textual justification models, but also better localizes the evidence that supports the decision. We also qualitatively show cases where visual explanation is more insightful than textual explanation, and vice versa, supporting our thesis that multimodal explanation models offer significant benefits over unimodal approaches.

View-based methods have achieved considerable success in $3$D object recognition tasks. Different from existing view-based methods pooling the view-wise features, we tackle this problem from the perspective of patches-to-patches similarity measurement. By exploiting the relationship between polynomial kernel and bilinear pooling, we obtain an effective $3$D object representation by aggregating local convolutional features through bilinear pooling. Meanwhile, we harmonize different components inherited in the pooled bilinear feature to obtain a more discriminative representation for a $3$D object. To achieve an end-to-end trainable framework, we incorporate the harmonized bilinear pooling operation as a layer of a network, constituting the proposed Multi-view Harmonized Bilinear Network (MHBN). Systematic experiments conducted on two public benchmark datasets demonstrate the efficacy of the proposed methods in $3$D object recognition.

We present a framework for learning single-view shape and pose prediction without using direct supervision for either. Our approach allows leveraging multi-view observations from unknown poses as supervisory signal during training. Our proposed training setup enforces geometric consistency between the independently predicted shape and pose from two views of the same instance. We consequently learn to predict shape in an emergent canonical (view-agnostic) frame along with a corresponding pose predictor. We show empirical and qualitative results using the ShapeNet dataset and observe encouragingly competitive performance to previous techniques which rely on stronger forms of supervision. We also demonstrate the applicability of our framework in a realistic setting which is beyond the scope of existing techniques: using a training dataset comprised of online product images where the underlying shape and pose are unknown.

We present a new multi-task learning (MTL) approach that can be applied to multiple heterogeneous task estimators. Our motivation is that the best task estimator could change depending on the task itself. For example, we may have a deep neural network for the first task and a Gaussian process for the second task. Classical MTL approaches cannot handle this case, as they require the same model or even the same parameter types for all tasks. We tackle this by considering task-specific estimators as random variables. Then, the task relationships are discovered by measuring the statistical dependence between each pair of random variables. By doing so, our model is independent of the parametric nature of each task, and is even agnostic to the existence of such parametric formulation. We compare our algorithm with existing MTL approaches on challenging real world ranking and regression datasets, and show that our approach achieves comparable or better performance without knowing the parametric form.

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.

We address the problem of image feature learning for the applications where multiple factors exist in the image generation process and only some factors are of our interest. We present a novel multi-task adversarial network based on an encoder-discriminator-generator architecture. The encoder extracts a disentangled feature representation for the factors of interest. The discriminators classify each of the factors as individual tasks. The encoder and the discriminators are trained cooperatively on factors of interest, but in an adversarial way on factors of distraction. The generator provides further regularization on the learned feature by reconstructing images with shared factors as the input image. We design a new optimization scheme to stabilize the adversarial optimization process when multiple distributions need to be aligned. The experiments on face recognition and font recognition tasks show that our method outperforms the state-of-the-art methods in terms of both recognizing the factors of interest and generalization to images with unseen variations.

Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem. Particularly, we train an agent to verify a pair of images at each time. The agent could choose to output the result (same or different) or request another pair of images to verify (unsure). By this way, our model implicitly learns the difficulty of image pairs, and postpone the decision when the model does not accumulate enough evidence. Moreover, by adjusting the reward for unsure action, we can easily trade off between speed and accuracy. In three open benchmarks, our method are competitive with the state-of-the-art methods while only using 3% to 6% images. These promising results demonstrate that our method is favorable in both efficiency and performance.

A prominent property of natural images is that groups of similar patches within them tend to lie on low-dimensional subspaces. This property has been previously used for image denoising, with particularly notable success via weighted nuclear norm minimization (WNNM). In this paper, we extend the WNNM method into a general image restoration algorithm, capable of handling arbitrary degradations (e.g. blur, missing pixels, etc.). Our approach is based on a novel regularization term which simultaneously penalizes for high weighted nuclear norm values of all the patch groups in the image. Our regularizer is isolated from the data-term, thus enabling convenient treatment of arbitrary degradations. Furthermore, it exploits the fractal property of natural images, by accounting for patch similarities also across different scales of the image. We propose a variable splitting method for solving the resulting optimization problem. This leads to an algorithm that is quite different from `plug-and-play' techniques, which solve image-restoration problems using a sequence of denoising steps. As we verify through extensive experiments, our algorithm achieves state of the art results in deblurring and inpainting, outperforming even the recent deep net based methods.

Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first order representation of object proposals for final classification and regression. Recent classification methods demonstrate that the integration of high order statistics into deep convolutional neural networks can achieve impressive improvement, but their goal is to model whole images by discarding location information so that they cannot be directly adopted to object detection. In this paper, we make an attempt to exploit high-order statistics in object detection, aiming at generating more discriminative representations for proposals to enhance the performance of detectors. To this end, we propose a novel Multi-scale Location-aware Kernel Representation (MLKP) to capture high-order statistics of deep features in proposals. Our MLKP can be efficiently computed on a modified multi-scale feature map using a low-dimensional polynomial kernel approximation. Moreover, different from existing orderless global representations based on high-order statistics, our proposed MLKP is location retentive and sensitive so that it can be flexibly adopted to object detection. Through integrating into Faster R-CNN schema, the proposed MLKP achieves very competitive performance with state-of-the-art methods, and improves Faster R-CNN by 4.9% (mAP), 4.7% (mAP) and 5.0 (AP at IOU=[0.5:0.05:0.95]) on PASCAL VOC 2007, VOC 2012 and MS COCO benchmarks, respectively. Code is available at: https://github.com/Hwang64/MLKP.

Previous deep learning based state-of-the-art scene text detection methods can be roughly classified into two categories. The first category treats scene text as a type of general objects and follows general object detection paradigm to localize scene text by regressing the text box locations, but troubled by the arbitrary-orientation and large aspect ratios of scene text. The second one segments text regions directly, but mostly needs complex post processing. In this paper, we present a method that combines the ideas of the two types of methods while avoiding their shortcomings. We propose to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions. In inference stage, candidate boxes are generated by sampling and grouping corner points, which are further scored by segmentation maps and suppressed by NMS. Compared with previous methods, our method can handle long oriented text naturally and doesn’t need complex post processing. The experiments on ICDAR2013, ICDAR2015, MSRA-TD500, MLT and COCO-Text demonstrate that the proposed algorithm achieves better or comparable results in both accuracy and efficiency. Based on VGG16, it achieves an F-measure of 84:3% on ICDAR2015 and 81:5% on MSRA-TD500.

In this paper, we present an end-to-end deep learning based framework for 3D object detection from a single monocular image. A deep convolutional neural network is introduced for simultaneous 2D and 3D object detection. First, 2D region proposals are generated through a region proposal network. Then the shared features are learned within the proposals to predict the class probability, 2D bounding box, orientation, dimension, and 3D location. We adopt a stand-alone module to predict the disparity and extract features from the computed point cloud. Thus features from the original image and the point cloud will be fused in different levels for accurate 3D localization. The estimated disparity is also used for front view feature encoding to enhance the input image,regarded as an input-fusionprocess. The proposed algorithm can directly output both 2D and 3D object detection results in an end-to-end fashion with only a single RGB image as the input. The experimental results on the challenging KITTI benchmark demonstrate that our algorithm significantly outperforms the state-of-the-art methods with only monocular images.

Key to effective person re-identification (Re-ID) is modelling discriminative and view-invariant factors of person appearance at both high and low semantic levels. Recently developed deep Re-ID models either learn a holistic single semantic level feature representation and/or require laborious human annotation of these factors as attributes. We propose Multi-Level Factorisation Net (MLFN), a novel network architecture that factorises the visual appearance of a person into latent discriminative factors at multiple semantic levels without manual annotation. MLFN is composed of multiple stacked blocks. Each block contains multiple factor modules to model latent factors at a specific level, and factor selection modules that dynamically select the factor modules to interpret the content of each input image. The outputs of the factor selection modules also provide a compact latent factor descriptor that is complementary to the conventional deeply learned features. MLFN achieves state-of-the-art results on three Re-ID datasets, as well as compelling results on the general object categorisation CIFAR-100 dataset.

In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a framework that incorporates knowledge graphs for describing the relationships between multiple labels. Our model learns an information propagation mechanism from the semantic label space, which can be applied to model the interdependencies between seen and unseen class labels. With such investigation of structured knowledge graphs for visual reasoning, we show that our model can be applied for solving multi-label classification and ML-ZSL tasks. Compared to state-of-the-art approaches, comparable or improved performances can be achieved by our method.

This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a sparse set of reliable features in the image collection. In this way, the proposed method is able to prune nonrepeatable features and also highly scalable to handle thousands of images. We additionally propose a low-rank constraint to ensure the geometric consistency of feature correspondences over the whole image collection. Besides the competitive performance on multi-graph matching and semantic flow benchmarks, we also demonstrate the applicability of the proposed method for reconstructing object-class models and discovering object-class landmarks from images without using any annotation.

The past few years have witnessed great success in applying deep learning to enhance the quality of compressed image/video. The existing approaches mainly focus on enhancing the quality of a single frame, ignoring the similarity between consecutive frames. In this paper, we investigate that heavy quality fluctuation exists across compressed video frames, and thus low quality frames can be enhanced using the neighboring high quality frames, seen as Multi-Frame Quality Enhancement (MFQE). Accordingly, this paper proposes an MFQE approach for compressed video, as a first attempt in this direction. In our approach, we firstly develop a Support Vector Machine (SVM) based detector to locate Peak Quality Frames (PQFs) in compressed video. Then, a novel Multi-Frame Convolutional Neural Network (MF-CNN) is designed to enhance the quality of compressed video, in which the non-PQF and its nearest two PQFs are as the input. The MF-CNN compensates motion between the non-PQF and PQFs through the Motion Compensation subnet (MC-subnet). Subsequently, the Quality Enhancement subnet (QE-subnet) reduces compression artifacts of the non-PQF with the help of its nearest PQFs. Finally, the experiments validate the effectiveness and generality of our MFQE approach in advancing the state-of-the-art quality enhancement of compressed video. The code of our MFQE approach is available at https://github.com/ryangBUAA/MFQE.git.

Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy achieved by top weakly supervised algorithms is still significantly lower than their fully supervised counterparts. In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation. In this pipeline, we first obtain intermediate object localization and pixel labeling results for the training images, and then use such results to train task-specific deep networks in a fully supervised manner. The entire process consists of four stages, including object localization in the training images, filtering and fusing object instances, pixel labeling for the training images, and task-specific network training. To obtain clean object instances in the training images, we propose a novel algorithm for filtering, fusing and classifying object instances collected from multiple solution mechanisms. In this algorithm, we incorporate both metric learning and density-based clustering to filter detected object instances. Experiments show that our weakly supervised pipeline achieves state-of-the-art results in multi-label image classification as well as weakly supervised object detection and very competitive results in weakly supervised semantic segmentation on MS-COCO, PASCAL VOC 2007 and PASCAL VOC 2012.

In recent years, many tracking algorithms achieve impressive performance via fusing multiple types of features, however, most of them fail to fully explore the context among the adopted multiple features and the strength of them. In this paper, we propose an efficient multi-cue analysis framework for robust visual tracking. By combining different types of features, our approach constructs multiple experts through Discriminative Correlation Filter (DCF) and each of them tracks the target independently. With the proposed robustness evaluation strategy, the suitable expert is selected for tracking in each frame. Furthermore, the divergence of multiple experts reveals the reliability of the current tracking, which is quantified to update the experts adaptively to keep them from corruption. Through the proposed multi-cue analysis, our tracker with standard DCF and deep features achieves outstanding results on several challenging benchmarks: OTB-2013, OTB-2015, Temple-Color and VOT 2016. On the other hand, when evaluated with only simple hand-crafted features, our method demonstrates comparable performance amongst complex non-realtime trackers, but exhibits much better efficiency, with a speed of 45 FPS on a CPU.

In this work, we focus on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface. To generate a set of multi-content images following a consistent style from very few examples, we propose an end-to-end stacked conditional GAN model considering content along channels and style along network layers. Our proposed network transfers the style of given glyphs to the contents of unseen ones, capturing highly stylized fonts found in the real-world such as those on movie posters or infographics. We seek to transfer both the typographic stylization (ex. serifs and ears) as well as the textual stylization (ex. color gradients and effects.) We base our experiments on our collected data set including 10,000 fonts with different styles and demonstrate effective generalization from a very small number of observed glyphs.

Detecting, counting, and classifying various cell types in images of human blood is important in many biomedical applications. However, these tasks can be very difficult due to the wide range of biological variability and the resolution limitations of many imaging modalities. This paper proposes a new approach to detecting, counting and classifying white blood cell populations in holographic images, which capitalizes on the fact that the variability in a mixture of blood cells is constrained by physiology. The proposed approach is based on a probabilistic generative model that describes an image of a population of cells as the sum of atoms from a convolutional dictionary of cell templates. The class of each template is drawn from a prior distribution that captures statistical information about blood cell mixtures. The parameters of the prior distribution are learned from a database of complete blood count results obtained from patients, and the cell templates are learned from images of purified cells from a single cell class using an extension of convolutional dictionary learning. Cell detection, counting and classification is then done using an extension of convolutional sparse coding that accounts for class proportion priors. This method has been successfully used to detect, count and classify white blood cell populations in holographic images of lysed blood obtained from 20 normal blood donors and 12 abnormal clinical blood discard samples. The error from our method is under 6.8% for all class populations, compared to errors of over 28.6% for all other methods tested.