works on

From the 1 of 22 linked papers with an AI index.

activity
20242026
collaborators
Showing 2025Show all

5 papers · 1 filter

cs.CV2025

LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration

Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe +4

In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based appro…

cs.CV2025

Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data

Yiqun Duan, Sameera Ramasinghe, Stephen Gould +1

Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural…

cs.LG2025

Nesterov Method for Asynchronous Pipeline Parallel Optimization

Thalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo +2

Pipeline Parallelism (PP) enables large neural network training on small, interconnected devices by splitting the model into multiple stages. To maximize pipeline utilization, asyn…

cs.CV2025

VI3NR: Variance Informed Initialization for Implicit Neural Representations

Chamin Hewa Koneputugodage, Yizhak Ben-Shabat, Sameera Ramasinghe +1

Implicit Neural Representations (INRs) are a versatile and powerful tool for encoding various forms of data, including images, videos, sound, and 3D shapes. A critical factor in th…

cs.CV2025

QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding

Binh M. Le, Shaoyuan Xu, Jinmiao Fu +6

In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify…