Searcharxiv⌕ Search

arXiv subjects

Han Hu

Publications and source records attributed to Han Hu.

At least 271 records · Page 15Linked to original sources
arXiv2020

Parametric Instance Classification for Unsupervised Visual Feature Learning

This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual-branch non-parametric fashion, PIC directly performs a one-branch parametric instance classification, revealing a simple framework similar to supervised classification and without the need to address the information leakage issue. We show that the simple PIC framework can be as effective as the state-of-the-art approaches, i.e. SimCLR and MoCo v2, by adapting several common component settings used in the state-of-the-art approaches. We also propose two novel techniques to further improve effectiveness and practicality of PIC: 1) a sliding-window data scheduler, instead of the previous epoch-based data scheduler, which addresses the extremely infrequent instance visiting issue in PIC and improves the effectiveness; 2) a negative sampling and weight update correction approach to reduce the training time and GPU memory consumption, which also enables application of PIC to almost unlimited training images. We hope that the PIC framework can serve as a simple baseline to facilitate future study.

cs.CV↗
arXiv2020

Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D Reconstruction

Integration of aerial and ground images has been proved as an efficient approach to enhance the surface reconstruction in urban environments. However, as the first step, the feature point matching between aerial and ground images is remarkably difficult, due to the large differences in viewpoint and illumination conditions. Previous studies based on geometry-aware image rectification have alleviated this problem, but the performance and convenience of this strategy is limited by several flaws, e.g. quadratic image pairs, segregated extraction of descriptors and occlusions. To address these problems, we propose a novel approach: leveraging photogrammetric mesh models for aerial-ground image matching. The methods of this proposed approach have linear time complexity with regard to the number of images, can explicitly handle low overlap using multi-view images and can be directly injected into off-the-shelf structure-from-motion (SfM) and multi-view stereo (MVS) solutions. First, aerial and ground images are reconstructed separately and initially co-registered through weak georeferencing data. Second, aerial models are rendered to the initial ground views, in which the color, depth and normal images are obtained. Then, the synthesized color images and the corresponding ground images are matched by comparing the descriptors, filtered by local geometrical information, and then propagated to the aerial views using depth images and patch-based matching. Experimental evaluations using various datasets confirm the superior performance of the proposed methods in aerial-ground image matching. In addition, incorporation of the existing SfM and MVS solutions into these methods enables more complete and accurate models to be directly obtained.

cs.CV↗
arXiv2020

Dense RepPoints: Representing Visual Objects with Dense Point Sets

We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these dense points, maintaining near-constant complexity with increasing point numbers. Dense RepPoints is shown to represent and learn object segments well, with the use of a novel distance transform sampling method combined with set-to-set supervision. The distance transform sampling combines the strengths of contour and grid representations, leading to performance that surpasses counterparts based on contours or grids. Code is available at \url{https://github.com/justimyhxu/Dense-RepPoints}.

cs.CV↗
arXiv2020

Fast and Regularized Reconstruction of Building Façades from Street-View Images using Binary Integer Programming

Regularized arrangement of primitives on building façades to aligned locations and consistent sizes is important towards structured reconstruction of urban environment. Mixed integer linear programing was used to solve the problem, however, it is extreamly time consuming even for state-of-the-art commercial solvers. Aiming to alleviate this issue, we cast the problem into binary integer programming, which omits the requirements for real value parameters and is more efficient to be solved . Firstly, the bounding boxes of the primitives are detected using the YOLOv3 architecture in real-time. Secondly, the coordinates of the upper left corners and the sizes of the bounding boxes are automatically clustered in a binary integer programming optimization, which jointly considers the geometric fitness, regularity and additional constraints; this step does not require \emph{a priori} knowledge, such as the number of clusters or pre-defined grammars. Finally, the regularized bounding boxes can be directly used to guide the façade reconstruction in an interactive envinronment. Experimental evaluations have revealed that the accuracies for the extraction of primitives are above 0.82, which is sufficient for the following 3D reconstruction. The proposed approach only takes about $ 10\% $ to $ 20\% $ of the runtime than previous approach and reduces the diversity of the bounding boxes to about $20\%$ to $50\%$.

cs.CV↗
arXiv2020

Ontology-based Interpretable Machine Learning for Textual Data

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is a major problem of long and complicated text data, we design a learnable anchor algorithm, to better extract explanations locally. A set of regulations is further introduced, regarding combining learned interpretable representations with anchors to generate comprehensible semantic explanations. An extensive experiment conducted on two real-world datasets shows that our approach generates more precise and insightful explanations compared with baseline approaches.

cs.LG↗
arXiv2020

Negative Margin Matters: Understanding Margin in Few-shot Classification

This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy on three standard few-shot classification benchmarks with few bells and whistles. These results are contrary to the common practice in the metric learning field, that the margin is zero or positive. To understand why the negative margin loss performs well for the few-shot classification, we analyze the discriminability of learned features w.r.t different margins for training and novel classes, both empirically and theoretically. We find that although negative margin reduces the feature discriminability for training classes, it may also avoid falsely mapping samples of the same novel class to multiple peaks or clusters, and thus benefit the discrimination of novel classes. Code is available at https://github.com/bl0/negative-margin.few-shot.

cs.CV↗
arXiv2020

Memory Enhanced Global-Local Aggregation for Video Object Detection

How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information. Recently, plenty of methods adopt the self-attention mechanisms to enhance the features in key frame with either global semantic information or local localization information. In this paper we introduce memory enhanced global-local aggregation (MEGA) network, which is among the first trials that takes full consideration of both global and local information. Furthermore, empowered by a novel and carefully-designed Long Range Memory (LRM) module, our proposed MEGA could enable the key frame to get access to much more content than any previous methods. Enhanced by these two sources of information, our method achieves state-of-the-art performance on ImageNet VID dataset. Code is available at \url{https://github.com/Scalsol/mega.pytorch}.

cs.CV↗
arXiv2020

Deep Fusion of Local and Non-Local Features for Precision Landslide Recognition

Precision mapping of landslide inventory is crucial for hazard mitigation. Most landslides generally co-exist with other confusing geological features, and the presence of such areas can only be inferred unambiguously at a large scale. In addition, local information is also important for the preservation of object boundaries. Aiming to solve this problem, this paper proposes an effective approach to fuse both local and non-local features to surmount the contextual problem. Built upon the U-Net architecture that is widely adopted in the remote sensing community, we utilize two additional modules. The first one uses dilated convolution and the corresponding atrous spatial pyramid pooling, which enlarged the receptive field without sacrificing spatial resolution or increasing memory usage. The second uses a scale attention mechanism to guide the up-sampling of features from the coarse level by a learned weight map. In implementation, the computational overhead against the original U-Net was only a few convolutional layers. Experimental evaluations revealed that the proposed method outperformed state-of-the-art general-purpose semantic segmentation approaches. Furthermore, ablation studies have shown that the two models afforded extensive enhancements in landslide-recognition performance.

eess.IV↗
arXiv2019

RepPoints: Point Set Representation for Object Detection

Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present \textbf{RepPoints} (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to automatically arrange themselves in a manner that bounds the spatial extent of an object and indicates semantically significant local areas. They furthermore do not require the use of anchors to sample a space of bounding boxes. We show that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 $AP_{50}$ on the COCO test-dev detection benchmark, using ResNet-101 model. Code is available at https://github.com/microsoft/RepPoints.

cs.CV↗
arXiv2019

XCMRC: Evaluating Cross-lingual Machine Reading Comprehension

We present XCMRC, the first public cross-lingual language understanding (XLU) benchmark which aims to test machines on their cross-lingual reading comprehension ability. To be specific, XCMRC is a Cross-lingual Cloze-style Machine Reading Comprehension task which requires the reader to fill in a missing word (we additionally provide ten noun candidates) in a sentence written in target language (English / Chinese) by reading a given passage written in source language (Chinese / English). Chinese and English are rich-resource language pairs, in order to study low-resource cross-lingual machine reading comprehension (XMRC), besides defining the common XCMRC task which has no restrictions on use of external language resources, we also define the pseudo low-resource XCMRC task by limiting the language resources to be used. In addition, we provide two baselines for common XCMRC task and two for pseudo XCMRC task respectively. We also provide an upper bound baseline for both tasks. We found that for common XCMRC task, translation-based method and multilingual sentence encoder-based method can obtain reasonable performance but still have much room for improvement. As for pseudo low-resource XCMRC task, due to strict restrictions on the use of language resources, our two approaches are far below the upper bound so there are many challenges ahead.

cs.CL↗
arXiv2019

Deep Metric Transfer for Label Propagation with Limited Annotated Data

We study object recognition under the constraint that each object class is only represented by very few observations. Semi-supervised learning, transfer learning, and few-shot recognition all concern with achieving fast generalization with few labeled data. In this paper, we propose a generic framework that utilizes unlabeled data to aid generalization for all three tasks. Our approach is to create much more training data through label propagation from the few labeled examples to a vast collection of unannotated images. The main contribution of the paper is that we show such a label propagation scheme can be highly effective when the similarity metric used for propagation is transferred from other related domains. We test various combinations of supervised and unsupervised metric learning methods with various label propagation algorithms. We find that our framework is very generic without being sensitive to any specific techniques. By taking advantage of unlabeled data in this way, we achieve significant improvements on all three tasks.

cs.CV↗
arXiv2019

Evaluating bird collision risk of a high-speed railway crossing the habitat of the crested ibis (Nipponia nippon) in Qinling Mountains, China

Bird collisions with high-speed transport modes is a vital topic on vehicle safety and wildlife protection, especially when high-speed trains, with an average speed of 250km/h, have to run across the habitat of an endangered bird species. This paper evaluates the bird-train collision risk associated with a recent high-speed railway project in Qinling Mountains, China, for the crested ibis (Nipponia nippon) and other local bird species. Using line transect surveys and walking monitoring techniques, we surveyed the population abundance, spatial-temporal distributions, and bridge-crossing behaviors of the birds in the study area. The results show that: (1) The crested ibis and the egret were the two most abundant waterfowl species in the study area. The RAI of these two species were about 43.69% and 42.91%, respectively; (2) Crested ibises overall habitat closer to the railway bridge. 91.63% of them were firstly detected within the range of 0m to 25m of the vicinity of the bridge; (3) the ratio between crossing over and under the railway bridge was about 7:3. Crested ibises were found to prefer to fly over the railway bridge (89.29% of the total crossing activities observed for this species). Egrets were more likely to cross the railway below the bridge, and they accounted for 60.27% of the total observations of crossing under the bridge. We recommend that, while the collision risk of crested ibises could be low, barrier-like structures, such as fences, should still be considered to promote the conservation of multiple bird species in the area. This paper provides a practical case for railway ecology studies in China. To our best knowledge, this is the first high-speed railway project that takes protecting crested ibises as one of the top priorities, and exemplifies the recent nationwide initiative towards the construction of "eco-civilization" in the country.

q-bio.PE↗
arXiv2019

Spatial-Temporal Relation Networks for Multi-Object Tracking

Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, making them hard to be combined in a unified network. As a result, existing methods usually encode them in separate networks or require a complex training approach. In this paper, we present a unified framework for similarity measurement which could simultaneously encode various cues and perform reasoning across both spatial and temporal domains. We also study the feature representation of a tracklet-object pair in depth, showing a proper design of the pair features can well empower the trackers. The resulting approach is named spatial-temporal relation networks (STRN). It runs in a feed-forward way and can be trained in an end-to-end manner. The state-of-the-art accuracy was achieved on all of the MOT15-17 benchmarks using public detection and online settings.

cs.CV↗
arXiv2019

Local Relation Networks for Image Recognition

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

cs.CV↗
arXiv2019

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at https://github.com/xvjiarui/GCNet.

cs.CV↗
arXiv2019

An Ensemble Deep Learning Model for Drug Abuse Detection in Sparse Twitter-Sphere

As the problem of drug abuse intensifies in the U.S., many studies that primarily utilize social media data, such as postings on Twitter, to study drug abuse-related activities use machine learning as a powerful tool for text classification and filtering. However, given the wide range of topics of Twitter users, tweets related to drug abuse are rare in most of the datasets. This imbalanced data remains a major issue in building effective tweet classifiers, and is especially obvious for studies that include abuse-related slang terms. In this study, we approach this problem by designing an ensemble deep learning model that leverages both word-level and character-level features to classify abuse-related tweets. Experiments are reported on a Twitter dataset, where we can configure the percentages of the two classes (abuse vs. non abuse) to simulate the data imbalance with different amplitudes. Results show that our ensemble deep learning models exhibit better performance than ensembles of traditional machine learning models, especially on heavily imbalanced datasets.

cs.SI↗
arXiv2018

Deformable ConvNets v2: More Deformable, Better Results

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation.

cs.CV↗