Signals 4 · free daily AI digest

Multimodal Taxonomic Conditioning for Generative Plankton Imagery

Paper recorded by Signals 4 on 2026-09-10 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11

Category: cs.CV · 计算机视觉 · first seen 2026-09-11

Abstract

Automated plankton imaging produces severely long-tailed datasets, where the rare taxa of greatest ecological interest have too few images to train or evaluate classifiers reliably. We generate synthetic plankton imagery conditioned on taxonomy: a CLIP encoder is adapted on a large plankton corpus with a ranked contrastive objective extended to deep, ragged taxonomies, then frozen to condition a p

Read on arXiv →

#87 most recent of 237 cs.CV papers we have recorded · ↑ newer: Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait E · ↓ older: Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Or
Cite this page: Multimodal Taxonomic Conditioning for Generative Plankton Imagery: the #87 most recent of 237 cs.CV papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/multimodal-taxonomic-conditioning-for-generative-plankton-imagery.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions