6 papers
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
Eunho Lee, Rei Kawakami, Youngbae Hwang
All-in-one image restoration seeks to recover clean images from inputs affected by diverse and unknown degradations using a unified framework. Recent methods have shown strong perf…
What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization
Ryota Yoshihashi, Masahiro Kada, Satoshi Ikehata +2
Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, a…
Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks
Ryo Moriai, Nakamasa Inoue, Masayuki Tanaka +3
Modern Hopfield networks (MHNs) have recently gained significant attention in the field of artificial intelligence because they can store and retrieve a large set of patterns with…
Multi-Point Positional Insertion Tuning for Small Object Detection
Kanoko Goto, Takumi Karasawa, Takumi Hirose +2
Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object dete…
GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields
Yusuke Sekikawa, Chingwei Hsu, Satoshi Ikehata +2
We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects. Pr…
ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks
Nakamasa Inoue, Shinta Otake, Takumi Hirose +2
Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recogniti…