Searcharxiv⌕ Search

arXiv subjects

Ning Xu

Publications and source records attributed to Ning Xu.

At least 127 records · Page 7Linked to original sources
arXiv2020

M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however, sequentially distill knowledge only from the last model, leading to performance degradation on the old classes in later incremental learning steps. In this paper, we propose a multi-model and multi-level knowledge distillation strategy. Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots. In addition, we incorporate an auxiliary distillation to further preserve knowledge encoded at the intermediate feature levels. To make the model more memory efficient, we adapt mask based pruning to reconstruct all previous models with a small memory footprint. Experiments on standard incremental learning benchmarks show that our method preserves the knowledge on old classes better and improves the overall performance over standard distillation techniques.

cs.CV↗
arXiv2020

Finding Action Tubes with a Sparse-to-Dense Framework

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor.

cs.CV↗
arXiv2020

CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes' location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors.

cs.CV↗
arXiv2020

Coupling between particle shape and long-range interaction in the high-density regime

By using long-range interacting polygons, we experimentally probe the coupling between particle shape and long-range interaction. For two typical space-filling polygons, square and triangle, we find two types of coupling modes that predominantly control the structure formation. Specifically, the rotational ordering of squares brings a lattice deformation that produces a hexagonal-to-rhombic transition in the high-density regime, whereas the alignment of triangles introduces a large geometric frustration that causes an order-to-disorder transition. Moreover, the two coupling modes lead to small and large "internal roughness" of the two systems, and thus predominantly control their structure relaxations. Our study thus provides a physical picture to the coupling between long-range interaction effect and short-range shape effect in the high-density regime unexplored before.

cond-mat.soft↗
arXiv2020

Video Question Answering on Screencast Tutorials

This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software. Unlike other video question answering works, all the answers in our dataset are grounded to the domain knowledge base. An one-shot recognition algorithm is designed to extract the visual cues, which helps enhance the performance of video question answering. We also propose several baseline neural network architectures based on various aspects of video contexts from the dataset. The experimental results demonstrate that our proposed models significantly improve the question answering performances by incorporating multi-modal contexts and domain knowledge.

cs.CL↗
arXiv2020

Rademacher upper bounds for cross-validation errors with an application to the lasso

We establish a general upper bound for $K$-fold cross-validation ($K$-CV) errors that can be adapted to many $K$-CV-based estimators and learning algorithms. Based on Rademacher complexity of the model and the Orlicz-$Ψ_ν$ norm of the error process, the CV error upper bound applies to both light-tail and heavy-tail error distributions. We also extend the CV error upper bound to $β$-mixing data using the technique of independent blocking. We provide a Python package (\texttt{CVbound}, \url{https://github.com/isaac2math}) for computing the CV error upper bound in $K$-CV-based algorithms. Using the lasso as an example, we demonstrate in simulations that the upper bounds are tight and stable across different parameter settings and random seeds. As well as accurately bounding the CV errors for the lasso, the minimizer of the new upper bounds can be used as a criterion for variable selection. Compared with the CV-error minimizer, simulations show that tuning the lasso penalty parameter according to the minimizer of the upper bound yields a more sparse and more stable model that retains all of the relevant variables.

stat.ML↗
arXiv2020

Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation

Autoregressive models recently achieved comparable results versus state-of-the-art Generative Adversarial Networks (GANs) with the help of Vector Quantized Variational AutoEncoders (VQ-VAE). However, autoregressive models have several limitations such as exposure bias and their training objective does not guarantee visual fidelity. To address these limitations, we propose to use Reinforced Adversarial Learning (RAL) based on policy gradient optimization for autoregressive models. By applying RAL, we enable a similar process for training and testing to address the exposure bias issue. In addition, visual fidelity has been further optimized with adversarial loss inspired by their strong counterparts: GANs. Due to the slow sampling speed of autoregressive models, we propose to use partial generation for faster training. RAL also empowers the collaboration between different modules of the VQ-VAE framework. To our best knowledge, the proposed method is first to enable adversarial learning in autoregressive models for image generation. Experiments on synthetic and real-world datasets show improvements over the MLE trained models. The proposed method improves both negative log-likelihood (NLL) and Fréchet Inception Distance (FID), which indicates improvements in terms of visual quality and diversity. The proposed method achieves state-of-the-art results on Celeba for 64 $\times$ 64 image resolution, showing promise for large scale image generation.

cs.CV↗
arXiv2020

Multiple Sound Sources Localization from Coarse to Fine

How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations. To solve this problem, we develop a two-stage audiovisual learning framework that disentangles audio and visual representations of different categories from complex scenes, then performs cross-modal feature alignment in a coarse-to-fine manner. Our model achieves state-of-the-art results on public dataset of localization, as well as considerable performance on multi-source sound localization in complex scenes. We then employ the localization results for sound separation and obtain comparable performance to existing methods. These outcomes demonstrate our model's ability in effectively aligning sounds with specific visual sources. Code is available at https://github.com/shvdiwnkozbw/Multi-Source-Sound-Localization

cs.CV↗
arXiv2020

AOWS: Adaptive and optimal network width search with latency constraints

Neural architecture search (NAS) approaches aim at automatically finding novel CNN architectures that fit computational constraints while maintaining a good performance on the target platform. We introduce a novel efficient one-shot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware. We first show that we can use a black-box approach to estimate a realistic latency model for a specific inference platform, without the need for low-level access to the inference computation. Then, we design a pairwise MRF to score any channel configuration and use dynamic programming to efficiently decode the best performing configuration, yielding an optimal solution for the network width search. Finally, we propose an adaptive channel configuration sampling scheme to gradually specialize the training phase to the target computational constraints. Experiments on ImageNet classification show that our approach can find networks fitting the resource constraints on different target platforms while improving accuracy over the state-of-the-art efficient networks.

cs.CV↗
arXiv2020

Minimizing FLOPs to Learn Efficient Sparse Representations

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging. Approximate methods based on learning compact representations, have been widely explored for this problem, such as locality sensitive hashing, product quantization, and PCA. In this work, in contrast to learning compact representations, we propose to learn high dimensional and sparse representations that have similar representational capacity as dense embeddings while being more efficient due to sparse matrix multiplication operations which can be much faster than dense multiplication. Following the key insight that the number of operations decreases quadratically with the sparsity of embeddings provided the non-zero entries are distributed uniformly across dimensions, we propose a novel approach to learn such distributed sparse embeddings via the use of a carefully constructed regularization function that directly minimizes a continuous relaxation of the number of floating-point operations (FLOPs) incurred during retrieval. Our experiments show that our approach is competitive to the other baselines and yields a similar or better speed-vs-accuracy tradeoff on practical datasets.

cs.LG↗
arXiv2020

Essential Norms of difference of generalized composition Operators from $α$-Bloch spaces to $β$-Bloch spaces

In this paper, we study the boundedness and essential norms of the differences of two generalized composition operators acting from $α$-Bloch space to $β$-Bloch space on the open unit disk. From essential norms, we get the compactness of the differences of two generalized composition operators. This study has a relationship to the topological structure of generalized composition operators acting from $α$-Bloch space to $β$-Bloch space.

math.CV↗
arXiv2020

Getting to 99% Accuracy in Interactive Segmentation

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.

cs.CV↗
arXiv2019

Large-scale Tag-based Font Retrieval with Generative Feature Learning

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.

cs.CV↗
arXiv2019

An Internal Learning Approach to Video Inpainting

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.

cs.CV↗
arXiv2019

Video Instance Segmentation

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.

cs.CV↗
arXiv2019

Adversarial Attacks in Sound Event Classification

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.

cs.LG↗
arXiv2019

Video Object Segmentation using Space-Time Memory Networks

We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods are unable to fully exploit this rich source of information. We resolve the issue by leveraging memory networks and learn to read relevant information from all available sources. In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory. Specifically, the query and the memory are densely matched in the feature space, covering all the space-time pixel locations in a feed-forward fashion. Contrast to the previous approaches, the abundant use of the guidance information allows us to better handle the challenges such as appearance changes and occlussions. We validate our method on the latest benchmark sets and achieved the state-of-the-art performance (overall score of 79.4 on Youtube-VOS val set, J of 88.7 and 79.2 on DAVIS 2016/2017 val set respectively) while having a fast runtime (0.16 second/frame on DAVIS 2016 val set).

cs.CV↗