Baochen Sun
YOU?
Author Swipe
View article: MoLA: MoE LoRA with Layer-wise Expert Allocation
MoLA: MoE LoRA with Layer-wise Expert Allocation Open
View article: Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond
Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond Open
The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background di…
View article: Higher Layers Need More LoRA Experts
Higher Layers Need More LoRA Experts Open
Parameter-efficient tuning (PEFT) techniques like low-rank adaptation (LoRA) offer training efficiency on Large Language Models, but their impact on model performance remains limited. Recent efforts integrate LoRA and Mixture-of-Experts (M…
View article: Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models
Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models Open
Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is…
View article: A Fast Minimization Algorithm for the Euler Elastica Model Based on a Bilinear Decomposition
A Fast Minimization Algorithm for the Euler Elastica Model Based on a Bilinear Decomposition Open
The Euler Elastica (EE) model with surface curvature can generate artifact-free results compared with the traditional total variation regularization model in image processing. However, strong nonlinearity and singularity due to the curvatu…
View article: LOWA: Localize Objects in the Wild with Attributes
LOWA: Localize Objects in the Wild with Attributes Open
We present LOWA, a novel method for localizing objects with attributes effectively in the wild. It aims to address the insufficiency of current open-vocabulary object detectors, which are limited by the lack of instance-level attribute cla…
View article: Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond
Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond Open
The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background di…
View article: Railway Polygonized Wheel Detection Based on Numerical Time-Frequency Analysis of Axle-Box Acceleration
Railway Polygonized Wheel Detection Based on Numerical Time-Frequency Analysis of Axle-Box Acceleration Open
The increasing need for repairs of polygonized wheels on high-speed railways in China is becoming problematic. At high speeds, polygonized wheels cause abnormal vibrations at the wheel-rail interface that can be detected via axle-box accel…