24 citations · 30 across the 30 of their papers we have counts for
8 papers · 1 filter
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization
Jiyoung Kim, Kyuhong Shim, Insu Lee +1
Unsupervised semantic segmentation (USS) aims to discover and recognize meaningful categories without any labels. For a successful USS, two key abilities are required: 1) informati…
Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data
Seunghan Yang, Byeonggeun Kim, Kyuhong Shim +1
Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords. However, existing KWS datasets are limited in scal…
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer
Kyuhong Shim, Jinkyu Lee, Simyung Chang +1
Streaming automatic speech recognition (ASR) models are restricted from accessing future context, which results in worse performance compared to the non-streaming models. To improv…
Depth-Relative Self Attention for Monocular Depth Estimation
Kyuhong Shim, Jiyoung Kim, Gusang Lee +1
Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on vario…
Semantic-Preserving Augmentation for Robust Image-Text Retrieval
Sunwoo Kim, Kyuhong Shim, Luong Trung Nguyen +1
Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and…
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers
Minsoo Kim, Kyuhong Shim, Seongmin Park +2
Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-awa…
Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning
Jiseob Kim, Kyuhong Shim, Junhan Kim +1
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the image attribute. In this paper, we put forth a new GZSL app…
Exploring Attention Map Reuse for Efficient Transformer Neural Networks
Kyuhong Shim, Jungwook Choi, Wonyong Sung
Transformer-based deep neural networks have achieved great success in various sequence applications due to their powerful ability to model long-range dependency. The key module of…