From the 1 of 22 linked papers with an AI index.
5 papers · 1 filter
MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
Minhyun Lee, Seungho Lee, Song Park +3
Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions.…
Masking meets Supervision: A Strong Learning Alliance
Byeongho Heo, Taekyung Kim, Sangdoo Yun +1
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentati…
Morphing Tokens Draw Strong Masked Image Models
Taekyung Kim, Byeongho Heo, Dongyoon Han
Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that ar…
Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
Jung Hyun Lee, June Yong Yang, Byeongho Heo +4
With the rapid advancement of test-time compute search strategies to improve the mathematical problem-solving capabilities of large language models (LLMs), the need for building ro…
DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias
Song Park, Sanghyuk Chun, Byeongho Heo +1
This paper argues that deep neural networks (DNNs) mostly determine their outputs during the early stages of inference, where biases inherent in the model play a crucial role in sh…