24 citations · 61 across the 13 of their papers we have counts for
16 papers
Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility
Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu +4
Upgrading embedding models typically requires expensive database re-indexing, as new query embeddings are incompatible with existing database embeddings. While Backward Compatible…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality
Chaofan Tao, Gukyeong Kwon, Varad Gunjal +7
We study the capability of Video-Language (VidL) models in understanding compositions between objects, attributes, actions and their relations. Composition understanding becomes pa…
Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Xingyu Fu, Sheng Zhang, Gukyeong Kwon +10
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Langua…
Masked Vision and Language Modeling for Multi-modal Representation Learning
Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran +3
In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling (MLM) and masked imag…
Patient Aware Active Learning for Fine-Grained OCT Classification
Yash-yee Logan, Ryan Benkert, Ahmad Mustafa +2
This paper considers making active learning more sensible from a medical perspective. In practice, a disease manifests itself in different forms across patient cohorts. Existing fr…
X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks
Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran +4
In this paper, we study the challenging instance-wise vision-language tasks, where the free-form language is required to align with the objects instead of the whole image. To addre…
Multi-Modal Learning Using Physicians Diagnostics for Optical Coherence Tomography Classification
Y. Logan, K. Kokilepersaud, G. Kwon +3
In this paper, we propose a framework that incorporates experts diagnostics and insights into the analysis of Optical Coherence Tomography (OCT) using multi-modal learning. To demo…
A Gating Model for Bias Calibration in Generalized Zero-shot Learning
Gukyeong Kwon, Ghassan AlRegib
Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a…
Novelty Detection Through Model-Based Characterization of Neural Networks
Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel +1
In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs tha…
Contrastive Explanations in Neural Networks
Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel +1
Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of th…
Backpropagated Gradient Representations for Anomaly Detection
Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel +1
Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use act…
Distorted Representation Space Characterization Through Backpropagated Gradients
Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel +1
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms. We demonstrate the utility of such gra…
Semantically Interpretable and Controllable Filter Sets
Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel +1
In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a vi…
Power of Tempospatially Unified Spectral Density for Perceptual Video Quality Assessment
Mohammed A. Aabed, Gukyeong Kwon, Ghassan AlRegib
We propose a perceptual video quality assessment (PVQA) metric for distorted videos by analyzing the power spectral density (PSD) of a group of pictures. This is an estimation appr…
CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition
Dogancan Temel, Gukyeong Kwon, Mohit Prabhushankar +1
In this paper, we investigate the robustness of traffic sign recognition algorithms under challenging conditions. Existing datasets are limited in terms of their size and challengi…