Oct 2026· International Conference on Computer Vision, Robotics, and Automation Engineering (CRAE 2026)· pp. 132· 0 citations
TL;DR
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.
Abstract
Few-Shot Object Detection (FSOD) requires models to recognize novel categories from scarce annotations. Existing methods rely on central semantic features, yet successive convolutions and pooling yield progressively smoothed features from object centers to edges, weakening boundary-background discrimination. Under few-shot conditions, models fail to reconstruct internal feature distributions and are forced to rely on boundary contours, making feature smoothing the critical performance bottleneck. We propose Self-Learning Edge Perception (SLEP), introducing self-learning edge perception into FSOD. SLEP comprises a learnable contour perception branch and an adaptive feature fusion gate, enabling the model to autonomously learn discriminative boundary patterns and dynamically couple semantic and contour information, thereby alleviating center-to-edge smoothing. Experiments on PASCAL VOC and MS COCO demonstrate that SLEP significantly outperforms TFA and other baselines on novel class detection.
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
Few-Shot Object Detection (FSOD) aims to achieve accurate detection of novel categories using only a few annotated samples. Among existing approaches, the Two-stage Fine-tuning Approach (TFA) exhibits good generalization capability, yet its training strategy—which relies on fixed feature representations—limits the mode...
Jin-Long Han, Yuan-Zhang Fan· International Conference on...· 0 citations
Open-vocabulary object detection aims to detect both seen and unseen categories by leveraging the semantic knowledge of vision-language models. However, existing methods often struggle with small objects due to insufficient preservation of high-resolution details, ineffective information aggregation across feature leve...
Han-Lin Kou, Bei-Qi Bai, Li Chen et al.· 0 citations
Few-shot object detection (FSOD) in remote sensing is challenged by discriminative feature dilution and label assignment imbalance due to tiny object sizes and scarce annotations. We propose a region-enhanced Gaussian receptive field (RGRF) network, a unified framework that jointly optimizes feature enhancement and sam...
Few-shot segmentation aims to segment novel object categories given only a handful of annotated examples. Existing approaches either rely on meta-trained specialist models whose learned matching functions generalize poorly across domains or adopt training-free pipelines based on point-wise feature similarity that treat...
Yi-Qi Wu, Hua-Chao Wu, Rong-Lei Hu et al.· Proceedings of the 34th ACM...· 0 citations
Real-time object detection under low illumination remains challenging because weak contrast, sensor noise, and feature degradation can reduce target discriminability, while practical deployment also requires careful control of model complexity and computational cost. Existing enhancement-then-detect pipelines can impro...
Min Hao, Zhe Chen, Ji-Long Li et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.