Join us tomorrow for the Joint Workshop on Marine Vision at #ICCV2025 (@iccv.bsky.social), from 9-6 in Room 318B!

Check out the full program here: vap.aau.dk/marinevision/

CODA is exceptionally label-efficient. On a benchmark suite of 26 different datasets, we show that CODA identifies the optimal or near-optimal model with fewer than 25 labeled examples over 50% of the time, and with fewer than 100 labeled examples over 80% of the time. 6/

CODA constructs a probabilistic model of which model is best at any labeling budget. To do this, we estimate confusion matrices for each candidate that we can 1) integrate over at any time to estimate which is best, and 2) update with new labels via Bayesian inference. 5/

Typically, answering the model selection question requires collecting a large test dataset to determine which candidate model is the best for you. CODA instead makes the process *active* – interactive, iterative, and guided by the models themselves. 3/

Adapt object detectors to new data *without labels* with Align and Distill (ALDI), our domain adaptation framework published last week in Transactions on Machine Learning Research (with a Featured Certification [Spotlight]!)