21 citations · 125 across the 18 of their papers we have counts for
20 papers
DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics
Dongyoon Ryu, Sungho Jeon, Xinyue Ma +4
Edge video analytics with lightweight models is prone to accuracy degradation due to persistent distributional shifts in live video streams. While continuous learning (CL) addresse…
Online Continual Learning on Hierarchical Label Expansion
Byung Hyun Lee, Okchul Jung, Jonghyun Choi +1
Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship…
Multi-Level Compositional Reasoning for Interactive Instruction Following
Suvaansh Bhambri, Byeonghwi Kim, Jonghyun Choi
Robotic agents performing domestic chores by natural language directives are required to master the complex job of navigating environment and interacting with objects in the enviro…
Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents
Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim +2
Accomplishing household tasks requires to plan step-by-step actions considering the consequences of previous actions. However, the state-of-the-art embodied agents often make mista…
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Xinyue Ma, Suyeon Jeong, Minjia Zhang +3
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hi…
Ask4Help: Learning to Leverage an Expert for Embodied Tasks
Kunal Pratap Singh, Luca Weihs, Alvaro Herrasti +3
Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable…
Attentive Fine-Grained Structured Sparsity for Image Restoration
Junghun Oh, Heewon Kim, Seungjun Nah +3
Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models. Despite the outstanding performance, the heavy computation dem…
Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
Jihwan Bang, Hyunseo Koh, Seulki Park +3
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, h…
Asymptotic behavior of the free interface for entire vector minimizers in phase transitions
Nicholas D. Alikakos, Zhiyuan Geng, Arghir Zarnescu
We study globally bounded entire minimizers of Allen-Cahn systems for potentials with and $W(u)\sim |u-a…
BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
Dahyun Kim, Kunal Pratap Singh, Jonghyun Choi
Backbone architectures of most binary networks are well-known floating point (FP) architectures such as the ResNet family. Questioning that the architectures designed for FP networ…
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
Hyunseo Koh, Dahyun Kim, Jung-Woo Ha +1
Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual…
Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning
Dahyun Kim, Jonghyun Choi
Self-supervised learning is a promising unsupervised learning framework that has achieved success with large floating point networks. But such networks are not readily deployable t…
Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
Soobee Lee, Minindu Weerakoon, Jonghyun Choi +3
Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks.…
Zero-shot Natural Language Video Localization
Jinwoo Nam, Daechul Ahn, Dongyeop Kang +2
Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries. To eliminate the annotation cost…
Rethinking Deep Image Prior for Denoising
Yeonsik Jo, Se Young Chun, Jonghyun Choi
Deep image prior (DIP) serves as a good inductive bias for diverse inverse problems. Among them, denoising is known to be particularly challenging for the DIP due to noise fitting…
Rainbow Memory: Continual Learning with a Memory of Diverse Samples
Jihwan Bang, Heesu Kim, YoungJoon Yoo +2
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realisti…
Factorizing Perception and Policy for Interactive Instruction Following
Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim +2
Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for AI agents. The 'interactive instruction following' ta…
Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence
Dahyun Kim, Jihwan Bae, Yeonsik Jo +1
Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned w…
Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
Tae-hoon Kim, Dongmin Kang, Kari Pulli +1
High-performance visual recognition systems generally require a large collection of labeled images to train. The expensive data curation can be an obstacle for improving recognitio…
ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
Tae-Hoon Kim, Jonghyun Choi
We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called Screen…