31 citations · 92 across the 12 of their papers we have counts for
12 papers
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
Sanghyun Jo, In-Jae Yu, Kyungsu Kim
Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels. However, mo…
Exploring Train and Test-Time Augmentations for Audio-Language Learning
Eungbeom Kim, Jinhee Kim, Yoori Oh +5
In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augme…
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
SungYub Kim, Sihwan Park, Kyungsu Kim +1
Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks. Flatness, defined as loss invariability…
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
Sanghyun Jo, In-Jae Yu, Kyungsu Kim
Although weakly supervised semantic segmentation using only image-level labels (WSSS-IL) is potentially useful, its low performance and implementation complexity still limit its ap…
Collaborative Method for Incremental Learning on Classification and Generation
Byungju Kim, Jaeyoung Lee, Kyungsu Kim +2
Although well-trained deep neural networks have shown remarkable performance on numerous tasks, they rapidly forget what they have learned as soon as they begin to learn with addit…
Modality Shifting Attention Network for Multi-modal Video Question Answering
Junyeong Kim, Minuk Ma, Trung Pham +2
This paper considers a network referred to as Modality Shifting Attention Network (MSAN) for Multimodal Video Question Answering (MVQA) task. MSAN decomposes the task into two sub-…
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
Jinseok Kim, Kyungsu Kim, Jae-Joon Kim
For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute th…
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
Hyungjun Kim, Kyungsu Kim, Jinseok Kim +1
Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings. However, BNNs suffer from performance degradation mainly due t…
Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling
Yunjae Jung, Dahun Kim, Sanghyun Woo +3
Visual storytelling is a task of creating a short story based on photo streams. Unlike existing visual captioning, storytelling aims to contain not only factual descriptions, but a…
Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering
Junyeong Kim, Minuk Ma, Kyungsu Kim +2
This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task t…
Progressive Attention Memory Network for Movie Story Question Answering
Junyeong Kim, Minuk Ma, Kyungsu Kim +2
This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpo…
Learning Not to Learn: Training Deep Neural Networks with Biased Data
Byungju Kim, Hyunwoo Kim, Kyungsu Kim +2
We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distrib…