collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

An accurate detection is not all you need to combat label noise in web-noisy datasets

Paul Albert, Jack Valmadre, Eric Arazo +3

Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical obse…

cs.CV20242 cited

Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation

Sidra Aleem, Fangyijie Wang, Mayug Maniparambil +6

The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domai…

cs.CV2024

ConvLoRA and AdaBN based Domain Adaptation via Self-Training

Sidra Aleem, Julia Dietlmeier, Eric Arazo +1

Existing domain adaptation (DA) methods often involve pre-training on the source domain and fine-tuning on the target domain. For multi-target domain adaptation, having a dedicated…

cs.CV2023

Self-Supervised and Semi-Supervised Polyp Segmentation using Synthetic Data

Enric Moreu, Eric Arazo, Kevin McGuinness +1

Early detection of colorectal polyps is of utmost importance for their treatment and for colorectal cancer prevention. Computer vision techniques have the potential to aid professi…

cs.CV20237 cited

Joint one-sided synthetic unpaired image translation and segmentation for colorectal cancer prevention

Enric Moreu, Eric Arazo, Kevin McGuinness +1

Deep learning has shown excellent performance in analysing medical images. However, datasets are difficult to obtain due privacy issues, standardization problems, and lack of annot…

cs.CV2022

Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets

Paul Albert, Eric Arazo, Noel E. O'Connor +1

Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrec…