Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection

• URL: http://arxiv.org/abs/2605.16406v1
• Date: Wed, 13 May 2026 10:41:55 GMT
• Title: Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection
• Abstract summary: We present Contrastive-SDXL, a day-to-night augmentation framework for night-time pedestrian detection.<n>To preserve semantic correspondence between daytime inputs and translated night-time images, we introduce a patch-wise semantic contrastive loss.<n> Detectors trained with our synthetic images obtain a 6-7% reduction in miss rate compared with a daytime-only baseline.
• Score: 2.833077175010763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only trained detectors unreliable. Latent diffusion models (LDMs) provide a powerful basis for image-to-image translation and cross-domain augmentation, but their effectiveness in safety-critical perception depends on whether detector-relevant objects and local semantic structure are preserved when translating between source and target domains. In this work, we present Contrastive-SDXL, a day-to-night augmentation framework for night-time pedestrian detection built on SDXL-Turbo and fine-tuned using Low-Rank Adaptation (LoRA). To preserve semantic correspondence between daytime inputs and translated night-time images, we introduce a patch-wise semantic contrastive loss guided by a pretrained DINOv2 encoder rather than generator encoder features. Multi-level DINOv2 self-attention maps enforce both local and global semantic consistency, while an object consistency loss explicitly encourages pedestrian preservation. Contrastive-SDXL produces realistic night-time images, achieving a Frechet Inception Distance (FID) of 22.5. Detectors trained with our synthetic images obtain a 6-7% reduction in miss rate compared with a daytime-only baseline, approaching the performance of detectors trained on real night-time data. These results demonstrate that consistency-driven diffusion augmentation can effectively support safety-critical night-time pedestrian detection.Specific

Related papers

• Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation [58.180226179087086]
  We propose a novel end-to-end optimized approach, named NightFormer, tailored for night-time semantic segmentation. Specifically, we design a pixel-level texture enhancement module to acquire texture-aware features hierarchically with phase enhancement and amplified attention. Our proposed method performs favorably against state-of-the-art night-time semantic segmentation methods.
  arXiv  Detail & Related papers  (2024-08-25T13:59:31Z)
• Disentangled Contrastive Image Translation for Nighttime Surveillance [87.03178320662592]
  Nighttime surveillance suffers from degradation due to poor illumination and arduous human annotations. Existing methods rely on multi-spectral images to perceive objects in the dark, which are troubled by low resolution and color absence. We argue that the ultimate solution for nighttime surveillance is night-to-day translation, or Night2Day. This paper contributes a new surveillance dataset called NightSuR. It includes six scenes to support the study on nighttime surveillance.
  arXiv  Detail & Related papers  (2023-07-11T06:40:27Z)
• LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation [5.961294477200831]
  We propose LoopDA for domain adaptive nighttime semantic segmentation. Our model outperforms prior methods on Dark Zurich and Nighttime Driving datasets for semantic segmentation.
  arXiv  Detail & Related papers  (2022-11-21T21:46:05Z)
• When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation [47.617222712429026]
  We show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth.
  arXiv  Detail & Related papers  (2022-06-28T09:29:55Z)
• Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion [51.11295961195151]
  We exploit the characteristics of the foggy image sequence of driving scenes to densify the confident pseudo labels. Based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion scheme. Our scheme helps the adaptive model achieve 51.92% and 53.84% mean intersection-over-union (mIoU) on two publicly available natural foggy datasets.
  arXiv  Detail & Related papers  (2022-06-10T05:16:50Z)
• Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images [60.89777029184023]
  We propose a semi-supervised CD model in which we formulate an unsupervised CD loss in addition to the supervised Cross-Entropy (CE) loss. Experiments conducted on two publicly available CD datasets show that the proposed semi-supervised CD method can reach closer to the performance of supervised CD.
  arXiv  Detail & Related papers  (2022-04-18T17:59:01Z)
• Unsupervised Domain Adaptation for Nighttime Aerial Tracking [27.595253191781904]
  This work develops a novel unsupervised domain adaptation framework for nighttime aerial tracking. A unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night.
  arXiv  Detail & Related papers  (2022-03-20T12:35:09Z)
• Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer [19.33490492872067]
  We propose a framework to alleviate the accuracy decline when object detection is taken to adverse conditions by using image translation method. To alleviate the detail corruptions caused by Generative Adversarial Networks (GANs), we propose to utilize Kernel Prediction Network (KPN) based method to refine the nighttime to daytime image translation.
  arXiv  Detail & Related papers  (2021-05-11T13:18:50Z)
• DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation [18.43890050736093]
  We propose a novel domain adaptation network (DANNet) for nighttime semantic segmentation. It employs an adversarial training with a labeled daytime dataset and an unlabeled dataset that contains coarsely aligned day-night image pairs. Our method achieves state-of-the-art performance for nighttime semantic segmentation.
  arXiv  Detail & Related papers  (2021-04-22T02:49:28Z)
• Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images [64.39996451133268]
  We present a semi-supervised approach for threat recognition which we call Background Adaptive Faster R-CNN. This approach is a training method for two-stage object detectors which uses Domain Adaptation methods from the field of deep learning. Two domain discriminators, one for discriminating object proposals and one for image features, are adversarially trained to prevent encoding domain-specific information. This can reduce threat detection false alarm rates by matching the statistics of extracted features from hand-collected backgrounds to real world data.
  arXiv  Detail & Related papers  (2020-10-02T21:05:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.