5 papers
AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels
Fengqiang Wan, Qing-Yuan Jiang, Yang Yang +1
Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training…
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
Guanhua Chen, Yutong Yao, Shenghe Sun +5
Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA)…
SR-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning
Fengqiang Wan, Yipeng Lin, Kan Lv +1
Pre-trained models with parameter-efficient fine-tuning (PEFT) have demonstrated promising potential for class-incremental learning (CIL), yet catastrophic forgetting still persist…
Not All LoRA Parameters Are Essential: Insights on Inference Necessity
Guanhua Chen, Yutong Yao, Ci-Jun Gao +3
Current research on LoRA primarily focuses on minimizing the number of fine-tuned parameters or optimizing its architecture. However, the necessity of all fine-tuned LoRA layers du…
The Solution for Single Object Tracking Task of Perception Test Challenge 2024
Zhiqiang Zhong, Yang Yang, Fengqiang Wan +2
This report presents our method for Single Object Tracking (SOT), which aims to track a specified object throughout a video sequence. We employ the LoRAT method. The essence of the…