614 citations · 2.1k across the 27 of their papers we have counts for
28 papers
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation
Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko +5
Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels. While there ex…
Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade +2
We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use…
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Donggyun Kim, Jinwoo Kim, Seongwoong Cho +2
Dense prediction tasks are a fundamental class of problems in computer vision. As supervised methods suffer from high pixel-wise labeling cost, a few-shot learning solution that ca…
Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers
Jaehoon Yoo, Semin Kim, Doyup Lee +2
Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos du…
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
Sungjun Cho, Seonwoo Min, Jinwoo Kim +3
To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under…
Equivariant Hypergraph Neural Networks
Jinwoo Kim, Saeyoon Oh, Sungjun Cho +1
Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations. Recent approaches for hypergraph learning extend…
Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon
Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attenti…
Pure Transformers are Powerful Graph Learners
Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min +4
We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat…
Learning Economic Indicators by Aggregating Multi-Level Geospatial Information
Sungwon Park, Sungwon Han, Donghyun Ahn +8
High-resolution daytime satellite imagery has become a promising source to study economic activities. These images display detailed terrain over large areas and allow zooming into…
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
Yoonki Cho, Woo Jae Kim, Seunghoon Hong +1
Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by us…
Learning to Generate Novel Classes for Deep Metric Learning
Kyungmoon Lee, Sungyeon Kim, Seunghoon Hong +1
Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However,…
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
Jaechang Kim, Yunjoo Lee, Seunghoon Hong +1
Audio super resolution aims to predict the missing high resolution components of the low resolution audio signals. While audio in nature is a continuous signal, current approaches…
Multi-Task Neural Processes
Donggyun Kim, Seongwoong Cho, Wonkwang Lee +1
Neural Processes (NPs) consider a task as a function realized from a stochastic process and flexibly adapt to unseen tasks through inference on functions. However, naive NPs can mo…
Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs
Jinwoo Kim, Saeyoon Oh, Seunghoon Hong
We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or…
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction
Wonkwang Lee, Whie Jung, Han Zhang +6
Learning to predict the long-term future of video frames is notoriously challenging due to inherent ambiguities in the distant future and dramatic amplifications of prediction erro…
SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data
Jinwoo Kim, Jaehoon Yoo, Juho Lee +1
Generative modeling of set-structured data, such as point clouds, requires reasoning over local and global structures at various scales. However, adopting multi-scale frameworks fo…
Variational Interaction Information Maximization for Cross-domain Disentanglement
HyeongJoo Hwang, Geon-Hyeong Kim, Seunghoon Hong +1
Cross-domain disentanglement is the problem of learning representations partitioned into domain-invariant and domain-specific representations, which is a key to successful domain t…
Improving Unsupervised Image Clustering With Robust Learning
Sungwon Park, Sungwon Han, Sundong Kim +4
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overc…
High-Fidelity Synthesis with Disentangled Representation
Wonkwang Lee, Donggyun Kim, Seunghoon Hong +1
Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disent…
Diversity-Sensitive Conditional Generative Adversarial Networks
Dingdong Yang, Seunghoon Hong, Yunseok Jang +2
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distribution…
Learning Hierarchical Semantic Image Manipulation through Structured Representations
Seunghoon Hong, Xinchen Yan, Thomas Huang +1
Understanding, reasoning, and manipulating semantic concepts of images have been a fundamental research problem for decades. Previous work mainly focused on direct manipulation on…
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
Seunghoon Hong, Dingdong Yang, Jongwook Choi +1
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout. Instead of learning a direct mapping from text to image, our algorithm decomposes…
Decomposing Motion and Content for Natural Video Sequence Prediction
Ruben Villegas, Jimei Yang, Seunghoon Hong +2
We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompos…
Weakly Supervised Semantic Segmentation using Web-Crawled Videos
Seunghoon Hong, Donghun Yeo, Suha Kwak +2
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained…