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

Source: [Language Prompt vs. Image Enhancement: Boosting Object Detection With CLIP in Hazy Environments](<https://www.sota2.com/research/paper/69ddca197d0172140ec79a3b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T05:00:11.244Z

Authors: Jian Pang, Bingfeng Zhang, Jin Wang, Baodi Liu, Dapeng Tao, Weifeng Liu

Published: 2026-04-12T13:26:59.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on TrashCan](<https://www.sota2.com/research/sota/object-detection-on-trashcan.md>): Object Detection; TrashCan; mAP: 59.63.

- [Object Detection on HazyCOCO](<https://www.sota2.com/research/sota/object-detection-on-hazycoco.md>): Object Detection; HazyCOCO; mAP: 44.92.

- [Object Detection on ExDark](<https://www.sota2.com/research/sota/object-detection-on-exdark.md>): Object Detection; ExDark; mAP (Mean Average Precision): 70.42.

- [Object Detection on RTTS](<https://www.sota2.com/research/sota/object-detection-on-rtts.md>): Object Detection; RTTS; mAP@50: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.10637>)

[PDF](<https://arxiv.org/pdf/2604.10637.pdf>)