CLIP language prompts guide a new weighted cross-entropy loss (CLIP-CE via AME and FAME) to boost object detection performance in hazy images, outperforming image enhancement baselines on the introduced HazyCOCO dataset.
Togethernet: Bridging image restoration and object detection together via dynamic enhancement learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FUN is an end-to-end Focal U-Net that performs joint hyperspectral image reconstruction and object detection via multi-task learning with focal modulation, achieving SOTA results with 40% fewer parameters and a new 363-image dataset.
citing papers explorer
-
Language Prompt vs. Image Enhancement: Boosting Object Detection With CLIP in Hazy Environments
CLIP language prompts guide a new weighted cross-entropy loss (CLIP-CE via AME and FAME) to boost object detection performance in hazy images, outperforming image enhancement baselines on the introduced HazyCOCO dataset.
-
FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging
FUN is an end-to-end Focal U-Net that performs joint hyperspectral image reconstruction and object detection via multi-task learning with focal modulation, achieving SOTA results with 40% fewer parameters and a new 363-image dataset.