6 papers
Large Language Models Facilitate Vision Reflection in Image Classification
Guoyuan An, JaeYoon Kim, SungEui Yoon
This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the predicti…
LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement
Xu Yin, Min-Sung Yoon, Yuchi Huo +2
Task execution for object rearrangement could be challenged by Task-Level Perturbations (TLP), i.e., unexpected object additions, removals, and displacements that can disrupt under…
OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning
Xu Yin, Fei Pan, Guoyuan An +3
Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from…
Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion
Guoyuan An, Yuchi Huo, Sung-Eui Yoon
This paper presents a novel method designed to enhance the efficiency and accuracy of both image retrieval and pixel retrieval. Traditional diffusion methods struggle to propagate…
Topological RANSAC for instance verification and retrieval without fine-tuning
Guoyuan An, Juhyung Seon, Inkyu An +2
This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable. The widely-used SPatial veri…
Towards Content-based Pixel Retrieval in Revisited Oxford and Paris
Guoyuan An, Woo Jae Kim, Saelyne Yang +3
This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel leve…