7 papers
Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
Atharv Goel, Sharat Agarwal, Saket Anand +1
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution s…
microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
Sathira Silva, Eman Ali, Chetan Arora +1
Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong…
Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR
Shashank Vempati, Nishit Anand, Gaurav Talebailkar +2
Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of con…
Enhancing Engagement and Learning in Computing Education: Automated Moodle-Based Problem-Solving Assessments
Charith Jayasekara, Carlo Kopp, Vincent Lee +1
This paper presents the design and refinement of automated Moodle-based Problem-Solving Assessments (PSAs) deployed across large-scale computing units. Developed to replace traditi…
Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation
Eman Ali, Chetan Arora, Muhammad Haris Khan
In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shif…
Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score
Eman Ali, Sathira Silva, Chetan Arora +1
Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised…