arXiv subjects

Geonmo Gu

Publications and source records attributed to Geonmo Gu.

25 records · Page 2Linked to original sources

arXiv2020

Symmetrical Synthesis for Deep Metric Learning

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard sample generation are adopting autoencoders or generative adversarial networks, but this leads to more hyper-parameters, harder optimization, and slower training speed. In this paper, we address these problems by proposing a novel method of synthetic hard sample generation called symmetrical synthesis. Given two original feature points from the same class, the proposed method firstly generates synthetic points with each other as an axis of symmetry. Secondly, it performs hard negative pair mining within the original and synthetic points to select a more informative negative pair for computing the metric learning loss. Our proposed method is hyper-parameter free and plug-and-play for existing metric learning losses without network modification. We demonstrate the superiority of our proposed method over existing methods for a variety of loss functions on clustering and image retrieval tasks. Our implementations is publicly available.

cs.CV↗

arXiv2020

Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on metric learning losses for augmentation and generalization. However, these methods require additional generative networks along with the main network, which can lead to a larger model size, slower training speed, and harder optimization. Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information. In this paper, inspired by query expansion and database augmentation, we propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair mining to learn with the most informative feature representations. Because of its simplicity and flexibility, it can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty. Finally, the combination of embedding expansion and representative metric learning losses outperforms the state-of-the-art losses and previous sample generation methods in both image retrieval and clustering tasks. The implementation is publicly available.

cs.CV↗

arXiv2020

Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at https://github.com/clovaai/assembled-cnn

cs.CV↗

arXiv2019

Fast Multiple Pattern Cartesian Tree Matching

Cartesian tree matching is the problem of finding all substrings in a given text which have the same Cartesian trees as that of a given pattern. In this paper, we deal with Cartesian tree matching for the case of multiple patterns. We present two fingerprinting methods, i.e., the parent-distance encoding and the binary encoding. By combining an efficient fingerprinting method and a conventional multiple string matching algorithm, we can efficiently solve multiple pattern Cartesian tree matching. We propose three practical algorithms for multiple pattern Cartesian tree matching based on the Wu-Manber algorithm, the Rabin-Karp algorithm, and the Alpha Skip Search algorithm, respectively. In the experiments we compare our solutions against the previous algorithm [18]. Our solutions run faster than the previous algorithm as the pattern lengths increase. Especially, our algorithm based on Wu-Manber runs up to 33 times faster.

cs.DS↗

arXiv2017

Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data

In face-related applications with a public available dataset, synthesizing non-linear facial variations (e.g., facial expression, head-pose, illumination, etc.) through a generative model is helpful in addressing the lack of training data. In reality, however, there is insufficient data to even train the generative model for face synthesis. In this paper, we propose Differential Generative Adversarial Networks (D-GAN) that can perform photo-realistic face synthesis even when training data is small. Two discriminators are devised to ensure the generator to approximate a face manifold, which can express face changes as it wants. Experimental results demonstrate that the proposed method is robust to the amount of training data and synthesized images are useful to improve the performance of a face expression classifier.

cs.CV↗

arXiv2017

Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image

In this paper, we propose Dynamics Transfer GAN; a new method for generating video sequences based on generative adversarial learning. The spatial constructs of a generated video sequence are acquired from the target image. The dynamics of the generated video sequence are imported from a source video sequence, with arbitrary motion, and imposed onto the target image. To preserve the spatial construct of the target image, the appearance of the source video sequence is suppressed and only the dynamics are obtained before being imposed onto the target image. That is achieved using the proposed appearance suppressed dynamics feature. Moreover, the spatial and temporal consistencies of the generated video sequence are verified via two discriminator networks. One discriminator validates the fidelity of the generated frames appearance, while the other validates the dynamic consistency of the generated video sequence. Experiments have been conducted to verify the quality of the video sequences generated by the proposed method. The results verified that Dynamics Transfer GAN successfully transferred arbitrary dynamics of the source video sequence onto a target image when generating the output video sequence. The experimental results also showed that Dynamics Transfer GAN maintained the spatial constructs (appearance) of the target image while generating spatially and temporally consistent video sequences.

cs.CV↗

arXiv2015

Fast Multiple Order-Preserving Matching Algorithms

Given a text $T$ and a pattern $P$, the order-preserving matching problem is to find all substrings in $T$ which have the same relative orders as $P$. Order-preserving matching has been an active research area since it was introduced by Kubica et al. \cite{kubica2013linear} and Kim et al. \cite{kim2014order}. In this paper we present two algorithms for the multiple order-preserving matching problem, one of which runs in sublinear time on average and the other in linear time on average. Both algorithms run much faster than the previous algorithms.

cs.DS↗