Sep 2026· IEEE Transactions on Image Processing· Vol 35, pp. 10773-10784· 0 citations· 83 references
Computer ScienceMedicine
TL;DR
A novel feature learning framework named DiffReID is proposed for object ReID that leverages a discriminative diffusion model to gradually learn identity-aware distributions and generate identity-invariant features.
Abstract
As a fundamental image processing task, object Re-Identification (ReID) aims to retrieve objects across non-overlapping cameras. Recently, with the development of deep learning, significant advancements have been made in object ReID. However, most existing methods suffer from generalization due to the limited size and diversity of ReID datasets. Meanwhile, current models tend to focus on extracting semantic patterns rather than learning identity-aware feature distributions. To address these issues, we propose a novel feature learning framework named DiffReID for object ReID. It leverages a discriminative diffusion model to gradually learn identity-aware distributions and generate identity-invariant features. More specifically, with the Contrastive Language-Image Pre-training (CLIP) model, we first obtain identity-aware text features by prompt tuning. Then, we propose a Vision-guided Noise Generator (VNG) to initialize probabilistic noises and gradually corrupt identity-aware text features. Afterwards, we take visual features as conditions and propose a Light Weight Denoiser (LWD) to denoise the corrupted text features step-by-step for identity-aware distribution learning. To obtain discriminative features, we further generate identity-invariant guided features from randomly sampling visual-guided noises. Finally, we propose a Mutual Enhancement Constraint (MEC) to facilitate mutual learning between visual features and guided features to enhance the representation robustness and discrimination. Extensive experiments on five object ReID benchmarks demonstrate that our method shows better results than most state-of-the-art methods. The source code will be publicly available.
Remote sensing object detection is fundamentally challenged by scale variations and background clutter. Existing discriminative methods often lack the generative comprehension needed to interpret ambiguous objects from incomplete visual cues. While adapting text-to-image diffusion models offers rich semantic priors to...
Fei-Yi Li, Xiao Zhang, Wen-Da Zhao· Proceedings of the 34th ACM...· 0 citations
Cross-domain few-shot object detection (CD-FSOD) presents a fundamental challenge: a detector must recognise novel object categories from as few as one to ten labelled examples per class, frequently in visual domains that differ substantially from the training distribution. Leading methods, such as CD-ViTO, address thi...
S. M. Deshmukh, Kailash A. Hambarde, Hugo Proença· Electronics· 0 citations
Object re-identification requires embeddings that are robust to intra-class variation in viewpoint, illumination, and occlusion, yet preserve sharp separation between visually similar identities. The hardest errors arise precisely where confusable identities meet, a region that pairwise losses shape only implicitly. We...
A. Psalta, V. Tsironis, K. Karantzalos· 0 citations
Self-Learning Edge Perception is proposed, introducing self-learning edge perception into FSOD, enabling the model to autonomously learn discriminative boundary patterns and dynamically couple semantic and contour information, thereby alleviating center-to-edge smoothing.
Recently, AI-generated image detection has gained increasing attention, as the rapid advancement of image generation technologies has raised serious concerns about their potential misuse. While existing detection methods have achieved promising results, their performance often degrades significantly when facing fake im...
Ju-Ye-On Kang, Jaehong Park, Semin Kim et al.· IEEE Access· 0 citations
A new domain adaptive person re-ID model DELTA (Deep Cluster with Attention Method) based on the unsupervised learning is proposed, which is more flexible and does not require additional annotations on the target domain.
Qing-Yu Wang, Ru-Chun Jia, Bo Peng et al.· Applied intelligence (Boston...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.