We propose GeoFusion, a SLAM-based scene estimation method for building an object-level semantic map in dense clutter. In dense clutter, objects are often in close contact and severe occlusions, which brings more false detections and noisy pose estimates from existing perception methods. To solve these problems, our key insight is to consider geometric consistency at the object level within a general SLAM framework. The geometric consistency is defined in two parts: geometric consistency score and geometric relation. The geometric consistency score describes the compatibility between object geometry model and observation point cloud. Meanwhile it provides a reliable measure to filter out false positives in data association. The geometric relation represents the relationship (e.g. contact) between geometric features (e.g. planes) among objects. The geometric relation makes the graph optimization for poses more robust and accurate. GeoFusion can robustly and efficiently infer the object labels, 6D object poses and spatial relations from continutous noisy semantic measurements. We quantitatively evaluate our method using observations from a Fetch mobile manipulation robot. Our results demonstrate greater robustness against false estimates than frame-by-frame pose estimation from the state-of-the-art convolutional neural network.
Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks. Yet, deep learning techniques tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets. We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow. We also show that significant improvements can be further gained by introducing a synthetic training dataset that is specifically designed for complex object boundaries. Comprehensive experiments support our approach, and our network achieves state of the art performance.
Prior work in multi-task learning has mainly focused on predictions on a single image. In this work, we present a new approach for multi-task learning from videos. Our approach contains a novel inter-frame attention module which allows learning of task-specific attention across frames. We embed the attention module in a "slow-fast" architecture, where the slower network runs on sparsely sampled keyframes and the lightweight shallow network runs on non-key frames at a high frame rate. We further propose an effective adversarial learning strategy to encourage the slow and fast network to learn similar features. The proposed architecture ensures low-latency multi-task learning while maintaining high quality prediction. Experiments show competitive accuracy compared to state-of-the-art on two multi-task learning benchmarks while reducing the number of floating point operations (FLOPs) by 70%. Meanwhile, our attention based feature propagation outperforms other feature propagation methods in accuracy by up to 90% reduction of FLOPs.
Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag relations. We propose a novel generative feature learning algorithm that leverages the unique characteristics of fonts. The key idea is that font images are synthetic and can therefore be controlled by the learning algorithm. We design an integrated rendering and learning process so that the visual feature from one image can be used to reconstruct another image with different text. The resulting feature captures important font design details while is robust to nuisance factors such as text. We propose a novel attention mechanism to re-weight the visual feature for joint visual-text modeling. We combine the feature and the attention mechanism in a novel recognition-retrieval model. Experimental results show that our method significantly outperforms the state-of-the-art for the important problem of large-scale tag-based font retrieval.
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images. In extending DIP to video we make two important contributions. First, we show that coherent video inpainting is possible without a priori training. We take a generative approach to inpainting based on internal (within-video) learning without reliance upon an external corpus of visual data to train a one-size-fits-all model for the large space of general videos. Second, we show that such a framework can jointly generate both appearance and flow, whilst exploiting these complementary modalities to ensure mutual consistency. We show that leveraging appearance statistics specific to each video achieves visually plausible results whilst handling the challenging problem of long-term consistency.
Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models trained for sound event classification. Four of the models use mel-spectrogram input and one model uses raw audio input. The models represent standard architectures such as convolutional, recurrent and dense networks. The dataset used for training is the Freesound dataset released for task 2 of the DCASE 2018 challenge and the models used are from participants of the challenge who open sourced their code. Our experiments show that adversarial attacks can be generated with high confidence and low perturbation. In addition, we show that the adversarial attacks are very effective across the different models.
In this paper we present a new computer vision task, named video instance segmentation. The goal of this new task is simultaneous detection, segmentation and tracking of instances in videos. In words, it is the first time that the image instance segmentation problem is extended to the video domain. To facilitate research on this new task, we propose a large-scale benchmark called YouTube-VIS, which consists of 2883 high-resolution YouTube videos, a 40-category label set and 131k high-quality instance masks. In addition, we propose a novel algorithm called MaskTrack R-CNN for this task. Our new method introduces a new tracking branch to Mask R-CNN to jointly perform the detection, segmentation and tracking tasks simultaneously. Finally, we evaluate the proposed method and several strong baselines on our new dataset. Experimental results clearly demonstrate the advantages of the proposed algorithm and reveal insight for future improvement. We believe the video instance segmentation task will motivate the community along the line of research for video understanding.