Chowdhury, Arpita
- MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
2024/07/23 by Kil, Jihyung, Mai, Zheda, Lee, Justin +6 · 13 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Fine-Tuning is Fine, if Calibrated
2024/09/24 by Zheda Mai, Arpita Chowdhury, Mai, Zheda +19 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
2025/01/16 by Arpita Chowdhury, Chowdhury, Arpita, Dipanjyoti Paul +23 · 5 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing and 3D Reconstruction
- Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
2025/01/20 by Zhang, Ziheng, Gu, Jianyang, Chowdhury, Arpita +5 · 3 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
2025/01/12 by Feng, Zhenyang, Wang, Zihe, Gu, Jianyang +22 · 1 citation
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
2025/06/10 by Mai, Zheda, Chowdhury, Arpita, Zihe Wang +10 · 2 citations
Computer Science · Materials Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science