mlsanityData to 14 Oct 2026

Language Prompt vs. Image Enhancement: Boosting Object Detection With CLIP in Hazy Environments

arXiv 2604.10637 ↗First posted 12 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Object detection in hazy environments is challenging because degraded objects are nearly invisible and their semantics are weakened by environmental noise, making it difficult for detectors to identify. Common approaches involve image enhancement to boost weakened semantics, but these methods are limited by the instability of enhanced modules. This paper proposes a novel solution by employing language prompts to enhance weakened semantics without image enhancement. Specifically, we design Approximation of Mutual Exclusion (AME) to provide credible weights for Cross-Entropy Loss, resulting in CLIP-guided Cross-Entropy Loss (CLIP-CE). The provided weights assess the semantic weakening of objects. Through the backpropagation of CLIP-CE, weakened semantics are enhanced, making degraded objects easier to detect. In addition, we present Fine-tuned AME (FAME) which adaptively fine-tunes the weight of AME based on the predicted confidence. The proposed FAME compensates for the imbalanced optimization in AME. Furthermore, we present HazyCOCO, a large-scale synthetic hazy dataset comprising 61258 images. Experimental results demonstrate that our method achieves state-of-the-art performance. The code and dataset will be released.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

28 of 47 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2018YOLOv3: An Incremental Improvementcited by 2,659
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  8. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  9. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  10. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  11. 2017Benchmarking Single Image Dehazing and Beyondcited by 447
  12. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 339
16 more
  1. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  2. 2018Getting to Know Low-light Images with The Exclusively Dark Datasetcited by 157
  3. 2021U-shape Transformer for Underwater Image Enhancementcited by 112
  4. 2023SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentationcited by 97
  5. 2021Image-Adaptive YOLO for Object Detection in Adverse Weather Conditionscited by 85
  6. 2022Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Modelscited by 40
  7. 2022GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditionscited by 20
  8. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  9. 2023Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identificationcited by 19
  10. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  11. 2023Simple Image-level Classification Improves Open-vocabulary Object Detectioncited by 15
  12. 2022Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detectioncited by 10
  13. 2022TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learningcited by 10
  14. 2024Fine-Grained Prototypes Distillation for Few-Shot Object Detectioncited by 10
  15. 2024Semi-supervised Open-World Object Detectioncited by 10
  16. 2024CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weathercited by 8

Built on by

Not cited yet.