AI Paper Atlas

Research map / Large language models / AI and society

CFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting

Madison Van Horn, Suzanne Stathatos, Sevan Brodjian, Justin Kay, Kai Van Brunt, Erik Young, Sara Beery, Pietro Perona, Michael Hobley

NeurIPS 2026 · Large language models › AI and society · approach: AI for health and public decisions · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces CFC26, an evaluation framework for automated fish counting from sonar videos aimed at field deployment.

Problem

Manual expert inspection of sonar videos to count fish populations is slow, expensive, and hard to reproduce, and existing automated counting systems lack deployment-oriented evaluation.

Approach

Builds evaluations (benchmark framing) for sonar-based fish counting intended to reflect real deployment conditions; the abstract is truncated so specifics are unknown.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add target-river data to multi-river training (Balanced ID vs OOD) (ablation)YOLOv5m + ByteTrack · MadnMAE: 0.800 -> 0.333Improved
add target-river data to multi-river training (ablation)YOLOv5m + ByteTrack · DungenessnMAE: 0.800 -> 0.000Improved
add target-river data to multi-river training (ablation)YOLOv5m + ByteTrack · EelnMAE: 1.000 -> 0.800No clear effect
add multi-river data on top of target-river-only training (ablation)YOLOv5m + ByteTrack · ChemainusnMAE: 0.49 -> 0.39Improved
train on target river only instead of all rivers (ablation)YOLOv5m + ByteTrack · NanaimonMAE: 0.120 -> 0.627Hurt
balanced ID training instead of selecting by nMAE: directional bias at ChemainusYOLOv5m + ByteTrack · ChemainusnMANE: nMAE 0.39 but nMANE -1.0Hurt
restrict training to CFC22 locations (geographically close to Dungeness) (ablation)YOLOv5m + ByteTrack · DungenessnMAE: 0.80 -> 0.20Improved
restrict training to CFC22 locations (ablation)YOLOv5m + ByteTrack · EelnMAE: nMAE approx 1.0Hurt
use 10k upsampled frames per location instead of no upsampling (ablation)YOLOv5m · CFC26 sampling comparisonnMAE: 0.11 -> 0.07Improved
replace YOLOv5m with RT-DETRv2-S (ablation)detector · CFC26 testnMAE: 0.0802 -> 0.0906No clear effect
replace YOLOv5 with YOLO26 (ablation)detector · CFC26 valmAP50: 0.6926 -> 0.6610 (medium)Hurt
vary ByteTrack hyperparameters (max age, min hits, IoU threshold) (ablation)ByteTrack · CFC26 all locationsnMAE: avg relative change 0.93% (min hits), 1.39% (IoU), 4.99% (max age)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy