Sangwoo Mo
YOU?
Author Swipe
View article: Open Ad-hoc Categorization with Contextualized Feature Learning
Open Ad-hoc Categorization with Contextualized Feature Learning Open
Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories are created dynamically to serve specific goals. We study open ad-hoc cat…
View article: SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs Open
Large language models (LLMs) have made significant advancements in various natural language processing tasks, including question answering (QA) tasks. While incorporating new information with the retrieval of relevant passages is a promisi…
View article: Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs Open
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks. However, a primary constraint they face is the context limit, i.e., the maximum number of tokens they can process. Previous works …
View article: S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions Open
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, an…
View article: RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data Open
Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data…
View article: Diffusion Probabilistic Models for Structured Node Classification
Diffusion Probabilistic Models for Structured Node Classification Open
This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels. In particular, we focus on solving the problem for partially labeled graphs where it is essential to i…
View article: Discovering and Mitigating Visual Biases through Keyword Explanation
Discovering and Mitigating Visual Biases through Keyword Explanation Open
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 statistic…
View article: OAMixer: Object-aware Mixing Layer for Vision Transformers
OAMixer: Object-aware Mixing Layer for Vision Transformers Open
Patch-based models, e.g., Vision Transformers (ViTs) and Mixers, have shown impressive results on various visual recognition tasks, alternating classic convolutional networks. While the initial patch-based models (ViTs) treated all patches…
View article: Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling Open
To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to ano…
View article: Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks Open
In the deep learning era, long video generation of high-quality still remains challenging due to the spatio-temporal complexity and continuity of videos. Existing prior works have attempted to model video distribution by representing video…
View article: Object-aware Contrastive Learning for Debiased Scene Representation
Object-aware Contrastive Learning for Debiased Scene Representation Open
Contrastive self-supervised learning has shown impressive results in learning
visual representations from unlabeled images by enforcing invariance against
different data augmentations. However, the learned representations are often
context…
View article: Object-aware Contrastive Learning for Debiased Scene Representation
Object-aware Contrastive Learning for Debiased Scene Representation Open
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often context…
View article: Abstract Reasoning via Logic-guided Generation
Abstract Reasoning via Logic-guided Generation Open
reasoning, i.e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence. While humans find the answer by either eliminating wrong candidates or first constructing the answer, …
View article: MASKER: Masked Keyword Regularization for Reliable Text Classification
MASKER: Masked Keyword Regularization for Reliable Text Classification Open
Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned t…
View article: MASKER: Masked Keyword Regularization for Reliable Text Classification
MASKER: Masked Keyword Regularization for Reliable Text Classification Open
Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned t…
View article: A Deeper Look at the Layerwise Sparsity of Magnitude-based Pruning.
A Deeper Look at the Layerwise Sparsity of Magnitude-based Pruning. Open
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without a clear consensus …
View article: Layer-adaptive sparsity for the Magnitude-based Pruning
Layer-adaptive sparsity for the Magnitude-based Pruning Open
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without a clear consensus …
View article: CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances Open
Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited fo…
View article: CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances Open
Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited fo…
View article: Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs Open
Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle…
View article: Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning
Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning Open
Magnitude-based pruning is one of the simplest methods for pruning neural networks. Despite its simplicity, magnitude-based pruning and its variants demonstrated remarkable performances for pruning modern architectures. Based on the observ…
View article: Mining GOLD Samples for Conditional GANs
Mining GOLD Samples for Conditional GANs Open
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach …
View article: InstaGAN: Instance-aware Image-to-Image Translation
InstaGAN: Instance-aware Image-to-Image Translation Open
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when…
View article: InstaGAN: Instance-aware Image-to-Image Translation
InstaGAN: Instance-aware Image-to-Image Translation Open
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when…
View article: Contextual Multi-armed Bandits under Feature Uncertainty
Contextual Multi-armed Bandits under Feature Uncertainty Open
We study contextual multi-armed bandit problems under linear realizability on rewards and uncertainty (or noise) on features. For the case of identical noise on features across actions, we propose an algorithm, coined NLinRel, having O(T⁷/…