3 citations · 12 across the 34 of their papers we have counts for
5 papers · 1 filter
CalibrateMix: Guided-Mixup Calibration of Image Semi-Supervised Models
Mehrab Mustafy Rahman, Jayanth Mohan, Tiberiu Sosea +1
Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL metho…
FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
Huitong Pan, Qi Zhang, Cornelia Caragea +2
Flowcharts are graphical tools for representing complex concepts in concise visual representations. This paper introduces the FlowLearn dataset, a resource tailored to enhance the…
EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM
Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan +5
In e-commerce, accurately extracting product attribute values from multimodal data is crucial for improving user experience and operational efficiency of retailers. However, previo…
ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction
Henry Peng Zou, Vinay Samuel, Yue Zhou +5
Existing datasets for attribute value extraction (AVE) predominantly focus on explicit attribute values while neglecting the implicit ones, lack product images, are often not publi…
MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins
Tiberiu Sosea, Cornelia Caragea
We introduce MarginMatch, a new SSL approach combining consistency regularization and pseudo-labeling, with its main novelty arising from the use of unlabeled data training dynamic…