arXiv subjects

Jianping Fan

Publications and source records attributed to Jianping Fan.

61 records · Page 4Linked to original sources

arXiv2018

NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification

This paper introduces a fast and efficient network architecture, NeXtVLAD, to aggregate frame-level features into a compact feature vector for large-scale video classification. Briefly speaking, the basic idea is to decompose a high-dimensional feature into a group of relatively low-dimensional vectors with attention before applying NetVLAD aggregation over time. This NeXtVLAD approach turns out to be both effective and parameter efficient in aggregating temporal information. In the 2nd Youtube-8M video understanding challenge, a single NeXtVLAD model with less than 80M parameters achieves a GAP score of 0.87846 in private leaderboard. A mixture of 3 NeXtVLAD models results in 0.88722, which is ranked 3rd over 394 teams. The code is publicly available at https://github.com/linrongc/youtube-8m.

cs.CV↗

arXiv2017

Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multi-modal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multi-modal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches. For fine-grained image and question representation, we develop a co-attention mechanism using an end-to-end deep network architecture to jointly learn both the image and question attentions. Combining the proposed MFB approach with co-attention learning in a new network architecture provides a unified model for VQA. Our experimental results demonstrate that the single MFB with co-attention model achieves new state-of-the-art performance on the real-world VQA dataset. Code available at https://github.com/yuzcccc/mfb.

cs.CV↗

arXiv2017

Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition

In this paper, a level-wise mixture model (LMM) is developed by embedding visual hierarchy with deep networks to support large-scale visual recognition (i.e., recognizing thousands or even tens of thousands of object classes), and a Bayesian approach is used to adapt a pre-trained visual hierarchy automatically to the improvements of deep features (that are used for image and object class representation) when more representative deep networks are learned along the time. Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative deep features for image and object class representation; (b) the tree classifier for recognizing large numbers of object classes hierarchically; and (c) the visual hierarchy adaptation for achieving more accurate indexing of large numbers of object classes hierarchically. By supporting joint learning of the tree classifier, the deep networks and the visual hierarchy adaptation, our LMM algorithm can provide an effective approach for controlling inter-level error propagation effectively, thus it can achieve better accuracy rates on large-scale visual recognition. Our experiments are carried on ImageNet1K and ImageNet10K image sets, and our LMM algorithm can achieve very competitive results on both the accuracy rates and the computation efficiency as compared with the baseline methods.

cs.CV↗

arXiv2017

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition

In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e.g., such base deep CNNs are trained to recognize different subsets of tens of thousands of atomic object classes. First, a two-layer (category layer and object class layer) ontology is constructed to achieve more effective solution for task group generation, e.g., assigning the semantically-related atomic object classes at the sibling leaf nodes into the same task group because they may share similar learning complexities. Second, one particular base deep CNNs with $M+1$ ($M \leq 1,000$) outputs is learned for each task group to recognize its $M$ atomic object classes effectively and identify one special class of "not-in-group" automatically, and the network structure (numbers of layers and units in each layer) of the well-designed AlexNet is directly used to configure such base deep CNNs. A deep multi-task learning algorithm is developed to leverage the inter-class visual similarities to learn more discriminative base deep CNNs and multi-task softmax for enhancing the separability of the atomic object classes in the same task group. Finally, all these base deep CNNs with diverse outputs (task spaces) are seamlessly combined to form a deep mixture of diverse experts for recognizing tens of thousands of atomic object classes. Our experimental results have demonstrated that our deep mixture of diverse experts algorithm can achieve very competitive results on large-scale visual recognition.

cs.CV↗

arXiv2016

Re-ranking Object Proposals for Object Detection in Automatic Driving

Object detection often suffers from a plenty of bootless proposals, selecting high quality proposals remains a great challenge. In this paper, we propose a semantic, class-specific approach to re-rank object proposals, which can consistently improve the recall performance even with less proposals. We first extract features for each proposal including semantic segmentation, stereo information, contextual information, CNN-based objectness and low-level cue, and then score them using class-specific weights learnt by Structured SVM. The advantages of the proposed model are twofold: 1) it can be easily merged to existing generators with few computational costs, and 2) it can achieve high recall rate uner strict critical even using less proposals. Experimental evaluation on the KITTI benchmark demonstrates that our approach significantly improves existing popular generators on recall performance. Moreover, in the experiment conducted for object detection, even with 1,500 proposals, our approach can still have higher average precision (AP) than baselines with 5,000 proposals.

cs.CV↗

arXiv2014

Efficiently Detecting Overlapping Communities through Seeding and Semi-Supervised Learning

Seeding then expanding is a commonly used scheme to discover overlapping communities in a network. Most seeding methods are either too complex to scale to large networks or too simple to select high-quality seeds, and the non-principled functions used by most expanding methods lead to poor performance when applied to diverse networks. This paper proposes a new method that transforms a network into a corpus where each edge is treated as a document, and all nodes of the network are treated as terms of the corpus. An effective seeding method is also proposed that selects seeds as a training set, then a principled expanding method based on semi-supervised learning is applied to classify edges. We compare our new algorithm with four other community detection algorithms on a wide range of synthetic and empirical networks. Experimental results show that the new algorithm can significantly improve clustering performance in most cases. Furthermore, the time complexity of the new algorithm is linear to the number of edges, and this low complexity makes the new algorithm scalable to large networks.

cs.SI↗

arXiv2011

HMTT: A Hybrid Hardware/Software Tracing System for Bridging Memory Trace's Semantic Gap

Memory trace analysis is an important technology for architecture research, system software (i.e., OS, compiler) optimization, and application performance improvements. Hardware-snooping is an effective and efficient approach to monitor and collect memory traces. Compared with software-based approaches, memory traces collected by hardware-based approaches are usually lack of semantic information, such as process/function/loop identifiers, virtual address and I/O access. In this paper we propose a hybrid hardware/software mechanism which is able to collect memory reference trace as well as semantic information. Based on this mechanism, we designed and implemented a prototype system called HMTT (Hybrid Memory Trace Tool) which adopts a DIMMsnooping mechanism to snoop on memory bus and a software-controlled tracing mechanism to inject semantic information into normal memory trace. To the best of our knowledge, the HMTT system is the first hardware tracing system capable of correlating memory trace with high-level events. Comprehensive validations and evaluations show that the HMTT system has both hardware's (e.g., no distortion or pollution) and software's advantages (e.g., flexibility and more information).

cs.AR↗