arXiv subjects

Minkyu Kim

Publications and source records attributed to Minkyu Kim.

At least 55 records · Page 3Linked to original sources

arXiv2024

Explicit Feature Interaction-aware Graph Neural Networks

Graph neural networks (GNNs) are powerful tools for handling graph-structured data. However, their design often limits them to learning only higher-order feature interactions, leaving low-order feature interactions overlooked. To address this problem, we introduce a novel GNN method called explicit feature interaction-aware graph neural network (EFI-GNN). Unlike conventional GNNs, EFI-GNN is a multilayer linear network designed to model arbitrary-order feature interactions explicitly within graphs. To validate the efficacy of EFI-GNN, we conduct experiments using various datasets. The experimental results demonstrate that EFI-GNN has competitive performance with existing GNNs, and when a GNN is jointly trained with EFI-GNN, predictive performance sees an improvement. Furthermore, the predictions made by EFI-GNN are interpretable, owing to its linear construction. The source code of EFI-GNN is available at https://github.com/gim4855744/EFI-GNN

cs.LG↗

arXiv2024

Impacts of Innovation School System in Korea: A Latent Space Item Response Model with Neyman-Scott Point Process

South Korea's educational system has faced criticism for its lack of focus on critical thinking and creativity, resulting in high levels of stress and anxiety among students. As part of the government's effort to improve the educational system, the innovation school system was introduced in 2009, which aims to develop students' creativity as well as their non-cognitive skills. To better understand the differences between innovation and regular school systems in South Korea, we propose a novel method that combines the latent space item response model (LSIRM) with the Neyman-Scott (NS) point process model. Our method accounts for the heterogeneity of items and students, captures relationships between respondents and items, and identifies item and student clusters that can provide a comprehensive understanding of students' behaviors/perceptions on non-cognitive outcomes. Our analysis reveals that students in the innovation school system show a higher sense of citizenship, while those in the regular school system tend to associate confidence in appearance with social ability. We compare our model with exploratory item factor analysis in terms of item clustering and find that our approach provides a more detailed and automated analysis. A comparison with exploratory item factor analysis highlights our method's advantages in terms of uncertainty quantification of the clustering process and more detailed and nuanced clustering results. Our method is made available to an existing R package, lsirm12pl.

stat.AP↗

arXiv2024

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity

Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images. These methods, however, tend to have significantly degraded pixel-wise fidelity, limiting their practicality. To fill this gap, we develop a new text-guided image compression algorithm that achieves both high perceptual and pixel-wise fidelity. In particular, we propose a compression framework that leverages text information mainly by text-adaptive encoding and training with joint image-text loss. By doing so, we avoid decoding based on text-guided generative models -- known for high generative diversity -- and effectively utilize the semantic information of text at a global level. Experimental results on various datasets show that our method can achieve high pixel-level and perceptual quality, with either human- or machine-generated captions. In particular, our method outperforms all baselines in terms of LPIPS, with some room for even more improvements when we use more carefully generated captions.

cs.CV↗

arXiv2024

Discovering and Mitigating Visual Biases through Keyword Explanation

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample statistics, which necessitates additional human supervision for interpretation. To tackle this issue, we propose the Bias-to-Text (B2T) framework, which interprets visual biases as keywords. Specifically, we extract common keywords from the captions of mispredicted images to identify potential biases in the model. We then validate these keywords by measuring their similarity to the mispredicted images using a vision-language scoring model. The keyword explanation form of visual bias offers several advantages, such as a clear group naming for bias discovery and a natural extension for debiasing using these group names. Our experiments demonstrate that B2T can identify known biases, such as gender bias in CelebA, background bias in Waterbirds, and distribution shifts in ImageNet-R/C. Additionally, B2T uncovers novel biases in larger datasets, such as Dollar Street and ImageNet. For example, we discovered a contextual bias between "bee" and "flower" in ImageNet. We also highlight various applications of B2T keywords, including debiased training, CLIP prompting, and model comparison.

cs.LG↗

arXiv2024

Image Clustering Conditioned on Text Criteria

Classical clustering methods do not provide users with direct control of the clustering results, and the clustering results may not be consistent with the relevant criterion that a user has in mind. In this work, we present a new methodology for performing image clustering based on user-specified text criteria by leveraging modern vision-language models and large language models. We call our method Image Clustering Conditioned on Text Criteria (IC|TC), and it represents a different paradigm of image clustering. IC|TC requires a minimal and practical degree of human intervention and grants the user significant control over the clustering results in return. Our experiments show that IC|TC can effectively cluster images with various criteria, such as human action, physical location, or the person's mood, while significantly outperforming baselines.

cs.CV↗

arXiv2024

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference

We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict problem of state-of-the-art mixed precision matrix multiplication kernels. Our method interleaves the quantized weight matrices of LLMs offline to skip the shared memory write-back after the dequantization. We demonstrate up to 1.91x speedup over existing kernels of AutoAWQ on larger batches and up to 1.94x throughput gain on representative LLM models on various NVIDIA GPU devices.

cs.LG↗

arXiv2024

On analytic exponential functors on free groups

This paper concerns exponential contravariant functors on free groups. We obtain an equivalence of categories between analytic, exponential contravariant functors on free groups and conilpotent cocommutative Hopf algebras. This result explains how equivalences of categories obtained previously by Pirashvili and by Powell interact. Moreover, we obtain an equivalence between the categories of outer, exponential contravariant functors on free groups and bicommutative Hopf algebras. We also go further by introducing a subclass of analytic, contravariant functors on free groups, called primitive functors; and prove an equivalence between primitive, exponential contravariant functors and primitive cocommutative Hopf algebras.

math.AT↗

arXiv2023

S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and adapting to such domains is challenging due to the limited number of image-text pairs available for training. To address this, we propose S-CLIP, a semi-supervised learning method for training CLIP that utilizes additional unpaired images. S-CLIP employs two pseudo-labeling strategies specifically designed for contrastive learning and the language modality. The caption-level pseudo-label is given by a combination of captions of paired images, obtained by solving an optimal transport problem between unpaired and paired images. The keyword-level pseudo-label is given by a keyword in the caption of the nearest paired image, trained through partial label learning that assumes a candidate set of labels for supervision instead of the exact one. By combining these objectives, S-CLIP significantly enhances the training of CLIP using only a few image-text pairs, as demonstrated in various specialist domains, including remote sensing, fashion, scientific figures, and comics. For instance, S-CLIP improves CLIP by 10% for zero-shot classification and 4% for image-text retrieval on the remote sensing benchmark, matching the performance of supervised CLIP while using three times fewer image-text pairs.

cs.CV↗

arXiv2023

LIVE: Lidar Informed Visual Search for Multiple Objects with Multiple Robots

This paper introduces LIVE: Lidar Informed Visual Search focused on the problem of multi-robot (MR) planning and execution for robust visual detection of multiple objects. We perform extensive real-world experiments with a two-robot team in an indoor apartment setting. LIVE acts as a perception module that detects unmapped obstacles, or Short Term Features (STFs), in Lidar observations. STFs are filtered, resulting in regions to be visually inspected by modifying plans online. Lidar Coverage Path Planning (CPP) is employed for generating highly efficient global plans for heterogeneous robot teams. Finally, we present a data model and a demonstration dataset, which can be found by visiting our project website https://sites.google.com/view/live-iros2023/home.

cs.RO↗

arXiv2023

Squeezing Large-Scale Diffusion Models for Mobile

The emergence of diffusion models has greatly broadened the scope of high-fidelity image synthesis, resulting in notable advancements in both practical implementation and academic research. With the active adoption of the model in various real-world applications, the need for on-device deployment has grown considerably. However, deploying large diffusion models such as Stable Diffusion with more than one billion parameters to mobile devices poses distinctive challenges due to the limited computational and memory resources, which may vary according to the device. In this paper, we present the challenges and solutions for deploying Stable Diffusion on mobile devices with TensorFlow Lite framework, which supports both iOS and Android devices. The resulting Mobile Stable Diffusion achieves the inference latency of smaller than 7 seconds for a 512x512 image generation on Android devices with mobile GPUs.

cs.LG↗

arXiv2023

Prefix tuning for automated audio captioning

Audio captioning aims to generate text descriptions from environmental sounds. One challenge of audio captioning is the difficulty of the generalization due to the lack of audio-text paired training data. In this work, we propose a simple yet effective method of dealing with small-scaled datasets by leveraging a pre-trained language model. We keep the language model frozen to maintain the expressivity for text generation, and we only learn to extract global and temporal features from the input audio. To bridge a modality gap between the audio features and the language model, we employ mapping networks that translate audio features to the continuous vectors the language model can understand, called prefixes. We evaluate our proposed method on the Clotho and AudioCaps dataset and show our method outperforms prior arts in diverse experimental settings.

eess.AS↗

arXiv2022

On a pair of extensions of Mayer-Vietoris functors

The purpose of this paper is to give a pair of canonical extensions of Mayer-Vietoris functors (e.g. homology or cohomology theories of spaces) to cospans of spaces. One of the pair, called cospanical extension in this paper, is closely related with the classical theory part of abelian Dijkgraaf-Witten-Freed-Quinn model and bicommutative Turaev-Viro-Barrett-Westbury model. We derive those extensions by revealing a partial universality of a cospan category of CW-spaces which is a homotopy-theoretic analogue of cobordism categories.

math.AT↗

arXiv2022

Pouch cells with 15% silicon calendar-aged for 4 years

Small amounts of high-capacity silicon-based materials are already used in the anode of commercial Li-ion batteries, helping increase their energy density. Despite their remarkable storage capability, silicon continuously reacts with the electrolyte, accelerating time-dependent cell performance fade. Nevertheless, very limited information is available on the specific consequences of this reactivity for the calendar aging of Li-ion cells. Here, we analyze aging effects on 450 mAh pouch cells containing 15 wt% of Si (and 73 wt% graphite) after storage at 21 oC for four years. We show that severe losses of Si capacity occurred due to particle isolation when cells were stored at high states of charge (SOC), but not when cells were fully discharged prior to storage. Impedance rise was also significantly higher when cells were kept at high SOCs and was mostly due to phenomena taking place at the cathode; the continuous electrolyte reduction at the anode did not lead to a major increase in bulk electrode resistance. A series of post-test characterization provided additional information on the effects of time and SOC on the calendar aging of Si-containing cells. Our study highlights the many challenges posed by Si during calendar aging and can inform future studies in the field.

physics.chem-ph↗

arXiv2022

The Lick Observatory Supernova Search follow-up program: photometry data release of 70 stripped-envelope supernovae

We present BVRI and unfiltered Clear light curves of 70 stripped-envelope supernovae (SESNe), observed between 2003 and 2020, from the Lick Observatory Supernova Search (LOSS) follow-up program. Our SESN sample consists of 19 spectroscopically normal SNe~Ib, two peculiar SNe Ib, six SN Ibn, 14 normal SNe Ic, one peculiar SN Ic, ten SNe Ic-BL, 15 SNe IIb, one ambiguous SN IIb/Ib/c, and two superluminous SNe. Our follow-up photometry has (on a per-SN basis) a mean coverage of 81 photometric points (median of 58 points) and a mean cadence of 3.6d (median of 1.2d). From our full sample, a subset of 38 SNe have pre-maximum coverage in at least one passband, allowing for the peak brightness of each SN in this subset to be quantitatively determined. We describe our data collection and processing techniques, with emphasis toward our automated photometry pipeline, from which we derive publicly available data products to enable and encourage further study by the community. Using these data products, we derive host-galaxy extinction values through the empirical colour evolution relationship and, for the first time, produce accurate rise-time measurements for a large sample of SESNe in both optical and infrared passbands. By modeling multiband light curves, we find that SNe Ic tend to have lower ejecta masses and lower ejecta velocities than SNe~Ib and IIb, but higher $^{56}$Ni masses.

astro-ph.HE↗

arXiv2022

KC-TSS: An Algorithm for Heterogeneous Robot Teams Performing Resilient Target Search

This paper proposes KC-TSS: K-Clustered-Traveling Salesman Based Search, a failure resilient path planning algorithm for heterogeneous robot teams performing target search in human environments. We separate the sample path generation problem into Heterogeneous Clustering and multiple Traveling Salesman Problems. This allows us to provide high-quality candidate paths (i.e. minimal backtracking, overlap) to an Information-Theoretic utility function for each agent. First, we generate waypoint candidates from map knowledge and a target prediction model. All of these candidates are clustered according to the number of agents and their ability to cover space, or coverage competency. Each agent solves a Traveling Salesman Problem (TSP) instance over their assigned cluster and then candidates are fed to a utility function for path selection. We perform extensive Gazebo simulations and preliminary deployment of real robots in indoor search and simulated rescue scenarios with static targets. We compare our proposed method against a state-of-the-art algorithm and show that ours is able to outperform it in mission time. Our method provides resilience in the event of single or multi teammate failure by recomputing global team plans online.

cs.RO↗

arXiv2021

Active Object Tracking using Context Estimation: Handling Occlusions and Detecting Missing Targets

When performing visual servoing or object tracking tasks, active sensor planning is essential to keep targets in sight or to relocate them when missing. In particular, when dealing with a known target missing from the sensor's field of view, we propose using prior knowledge related to contextual information to estimate its possible location. To this end, this study proposes a Dynamic Bayesian Network that uses contextual information to effectively search for targets. Monte Carlo particle filtering is employed to approximate the posterior probability of the target's state, from which uncertainty is defined. We define the robot's utility function via information-theoretic formalism as seeking the optimal action which reduces uncertainty of a task, prompting robot agents to investigate the location where the target most likely might exist. Using a context state model, we design the agent's high-level decision framework using a Partially-Observable Markov Decision Process. Based on the estimated belief state of the context via sequential observations, the robot's navigation actions are determined to conduct exploratory and detection tasks. By using this multi-modal context model, our agent can effectively handle basic dynamic events, such as obstruction of targets or their absence from the field of view. We implement and demonstrate these capabilities on a mobile robot in real-time.

cs.RO↗

arXiv2021

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the prediction confidence, i.e., the higher confidence from a smoothed classifier implies the better robustness. This motivates us to rethink the fundamental trade-off between accuracy and robustness in terms of calibrating confidences of a smoothed classifier. In this paper, we propose a simple training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup: it trains on convex combinations of samples along the direction of adversarial perturbation for each input. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness in case of smoothed classifiers, and offers an intuitive way to adaptively set a new decision boundary between these samples for better robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified $\ell_2$-robustness of smoothed classifiers compared to existing state-of-the-art robust training methods.

cs.LG↗

arXiv2021

Global-Local Item Embedding for Temporal Set Prediction

Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e.g., personalized purchase prediction of shopping baskets. While most previous techniques have focused on leveraging a user's history, the study of combining it with others' histories remains untapped potential. This paper proposes Global-Local Item Embedding (GLOIE) that learns to utilize the temporal properties of sets across whole users as well as within a user by coining the names as global and local information to distinguish the two temporal patterns. GLOIE uses Variational Autoencoder (VAE) and dynamic graph-based model to capture global and local information and then applies attention to integrate resulting item embeddings. Additionally, we propose to use Tweedie output for the decoder of VAE as it can easily model zero-inflated and long-tailed distribution, which is more suitable for several real-world data distributions than Gaussian or multinomial counterparts. When evaluated on three public benchmarks, our algorithm consistently outperforms previous state-of-the-art methods in most ranking metrics.

cs.LG↗