5 papers
Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism
Gunho Jung, Jeong-Woo Park, Seon Bin Kim +1
Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction. In a training-free zero-shot s…
ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models
Singon Kim, Gunho Jung, Seong-Whan Lee
Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However,retrieved…
Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition
Gunho Jung, Heejo Kong, Seong-Whan Lee
Dynamic facial expression recognition (DFER) aims to identify emotional states by modeling the temporal changes in facial movements across video sequences. A key challenge in DFER…
RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation
Geon Park, Seon Bin Kim, Gunho Jung +1
With recent advancements in text-to-image (T2I) models, effectively generating multiple instances within a single image prompt has become a crucial challenge. Existing methods, whi…
Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
Heejo Kong, Sung-Jin Kim, Gunho Jung +1
Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily vi…