Author name cluster

Geonmo Gu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

TMLR Journal 2024 Journal Article

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Geonmo Gu
Sanghyuk Chun
Wonjae Kim
HeeJae Jun
Yoohoon Kang
Sangdoo Yun

This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset samples are available at https://github.com/navervision/CompoDiff.

PDF Details

AAAI Conference 2022 Conference Paper

Towards Light-Weight and Real-Time Line Segment Detection

Geonmo Gu
Byungsoo Ko
SeoungHyun Go
Sung-Hyun Lee
Jingeun Lee
Minchul Shin

Previous deep learning-based line segment detection (LSD) suffers from the immense model size and high computational cost for line prediction. This constrains them from real-time inference on computationally restricted environments. In this paper, we propose a real-time and light-weight line segment detector for resource-constrained environments named Mobile LSD (M-LSD). We design an extremely efficient LSD architecture by minimizing the backbone network and removing the typical multi-module process for line prediction found in previous methods. To maintain competitive performance with a light-weight network, we present novel training schemes: Segments of Line segment (SoL) augmentation, matching and geometric loss. SoL augmentation splits a line segment into multiple subparts, which are used to provide auxiliary line data during the training process. Moreover, the matching and geometric loss allow a model to capture additional geometric cues. Compared with TP-LSD-Lite, previously the best real-time LSD method, our model (M-LSDtiny) achieves competitive performance with 2. 5% of model size and an increase of 130. 5% in inference speed on GPU. Furthermore, our model runs at 56. 8 FPS and 48. 6 FPS on the latest Android and iPhone mobile devices, respectively. To the best of our knowledge, this is the first real-time deep LSD available on mobile devices.

PDF Details

TCS Journal 2021 Journal Article

Fast algorithms for single and multiple pattern Cartesian tree matching

Siwoo Song
Geonmo Gu
Cheol Ryu
Simone Faro
Thierry Lecroq
Kunsoo Park

Cartesian tree matching is the problem of finding every substring of a given text which has the same Cartesian tree as that of a given pattern. In this paper we propose fast algorithms for single and multiple pattern Cartesian tree matching by introducing new representations and encodings. For single pattern Cartesian tree matching, we present the framework of a binary filtration method and an efficient verification technique. Any exact string matching algorithm can be used as a filtration for Cartesian tree matching in our framework. For multiple pattern Cartesian tree matching, 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. By experiments we show that our matching algorithms provide good performances for both single and multiple pattern Cartesian tree matching.

Details DOI

AAAI Conference 2021 Conference Paper

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning

Geonmo Gu
Byungsoo Ko
Han-Gyu Kim

One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes. Most existing works have tried to achieve this using different types of metric objectives and hard sample mining strategies with given training data. However, learning with only the training data can be overfitted to the seen classes, leading to the lack of generalization capability on unseen classes. To address this problem, we propose a simple regularizer called Proxy Synthesis that exploits synthetic classes for stronger generalization in deep metric learning. The proposed method generates synthetic embeddings and proxies that work as synthetic classes, and they mimic unseen classes when computing proxy-based losses. Proxy Synthesis derives an embedding space considering class relations and smooth decision boundaries for robustness on unseen classes. Our method is applicable to any proxy-based losses, including softmax and its variants. Extensive experiments on four famous benchmarks in image retrieval tasks demonstrate that Proxy Synthesis significantly boosts the performance of proxy-based losses and achieves state-of-the-art performance. Our implementation is available at github. com/navervision/proxy-synthesis.

PDF Details

AAAI Conference 2020 Conference Paper

Symmetrical Synthesis for Deep Metric Learning

Geonmo Gu
Byungsoo Ko

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 hyperparameters, 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 hyperparameter 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.

PDF Details