Search Results for author: Minsoo Kim

Found 16 papers, 6 papers with code

VIGFace: Virtual Identity Generation Model for Face Image Synthesis

no code implementations13 Mar 2024 Minsoo Kim, Min-Cheol Sagong, Gi Pyo Nam, Junghyun Cho, Ig-Jae Kim

Initially, we train the face recognition model using a real face dataset and create a feature space for both real and virtual IDs where virtual prototypes are orthogonal to other prototypes.

Face Recognition Image Generation

Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization

no code implementations9 Nov 2023 Jangwhan Lee, Minsoo Kim, SeungCheol Baek, Seok Joong Hwang, Wonyong Sung, Jungwook Choi

Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands.

Computational Efficiency Quantization

Self-supervised Equality Embedded Deep Lagrange Dual for Approximate Constrained Optimization

no code implementations11 Jun 2023 Minsoo Kim, HongSeok Kim

Furthermore, we prove the convergence of DeepLDE and show that the primal-dual learning method alone cannot ensure equality constraints without the help of equality embedding.

Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding

no code implementations CVPR 2023 Minyoung Hwang, Jaeyeon Jeong, Minsoo Kim, Yoonseon Oh, Songhwai Oh

We show that an exploitation policy, which moves the agent toward a well-chosen local goal among unvisited but observable states, outperforms a method which moves the agent to a previously visited state.

Vision and Language Navigation Visual Navigation

Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers

1 code implementation23 Feb 2023 Minsoo Kim, Kyuhong Shim, Seongmin Park, Wonyong Sung, Jungwook Choi

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.

Knowledge Distillation Quantization

Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders

1 code implementation20 Nov 2022 Minsoo Kim, Sihwa Lee, Sukjin Hong, Du-Seong Chang, Jungwook Choi

In particular, KD has been employed in quantization-aware training (QAT) of Transformer encoders like BERT to improve the accuracy of the student model with the reduced-precision weight parameters.

Knowledge Distillation Model Compression +1

Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption

no code implementations NAACL 2022 Garam Lee, Minsoo Kim, Jai Hyun Park, Seung-won Hwang, Jung Hee Cheon

Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy.

Privacy Preserving text-classification +1

SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning

no code implementations22 Sep 2022 Eunkyu Oh, Taehun Kim, Minsoo Kim, Yunhu Ji, Sushil Khyalia

As a crucial component of contrastive learning, we propose two global context enhanced data augmentation methods while maintaining the semantics of the original session.

Contrastive Learning Data Augmentation +1

Collective Relevance Labeling for Passage Retrieval

1 code implementation NAACL 2022 Jihyuk Kim, Minsoo Kim, Seung-won Hwang

Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document relevance labels, but such labels are inherently sparse.

Knowledge Distillation Passage Retrieval +1

NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference

no code implementations3 Dec 2021 Joonsang Yu, Junki Park, Seongmin Park, Minsoo Kim, Sihwa Lee, Dong Hyun Lee, Jungwook Choi

Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models.

A 3D model-based approach for fitting masks to faces in the wild

1 code implementation1 Mar 2021 Je Hyeong Hong, Hanjo Kim, Minsoo Kim, Gi Pyo Nam, Junghyun Cho, Hyeong-Seok Ko, Ig-Jae Kim

Our method proceeds by first fitting a 3D morphable model on the input image, second overlaying the mask surface onto the face model and warping the respective mask texture, and last projecting the 3D mask back to 2D.

Face Model Face Recognition

A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology

1 code implementation21 Dec 2016 Kyunghyun Paeng, Sangheum Hwang, Sunggyun Park, Minsoo Kim

We present a unified framework to predict tumor proliferation scores from breast histopathology whole slide images.

Mitosis Detection whole slide images

Towards Abstraction from Extraction: Multiple Timescale Gated Recurrent Unit for Summarization

no code implementations WS 2016 Minsoo Kim, Moirangthem Dennis Singh, Minho Lee

The results also show that the temporal hierarchies help improve the ability of seq2seq models to capture compositionalities better without the presence of highly complex architectural hierarchies.

Abstractive Text Summarization Decoder

Cannot find the paper you are looking for? You can Submit a new open access paper.