← Back to all news
arXiv Computer Vision By Muhammad Ibraheem Siddiqui, Muhammad Haris Khan

CountZES: Counting via Zero-Shot Exemplar Discovery and Selection

Read the original on arXiv Computer Vision →

CountZES is an inference‑only framework for zero‑shot object counting that jointly discovers and selects exemplars through density‑guided candidate generation and complementary selection mechanisms. It progresses through three stages—Detection‑Anchored Exemplar, Density‑Guided Exemplar, and Feature‑Consensus Exemplar—to build reliable single‑instance anchors, expand candidate discovery beyond detector constraints, and promote feature‑level representativeness. The method achieves strong cross‑domain generalization and outperforms other inference‑only zero‑shot counting approaches across natural, aerial, and medical datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 26

Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR

arXiv:2608.24281v1 Announce Type: new Abstract: Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object de...

By Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Mathias Zinnen, Pranjal Sahu, Florin C. Ghesu, Sasa Grbic, Andreas Maier
computer-visionmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 17

DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting

DualCount introduces an instance-aware dual-decoder framework that couples density and point representations for zero‑shot object counting. By treating density estimation as a structured mass allocation over latent object instances, it applies two geometric constraints—per‑instance mass conservation and center‑of‑mass alignment—to enforce instance‑level consistency. Experiments on FSC‑147, PUCPR+, and CARPK demonstrate that this approach consistently reduces counting error and achieves new state‑of‑the‑art performance.

By Xuan Cuong Ngo
benchmarkssafety
More like this →
arXiv Computer Vision
4d ago

FocusOVD: Geometric and Contextual Feature Refinement for Open-Vocabulary Small-Object Detection

FocusOVD is an open‑vocabulary object detector that improves small‑object detection by refining geometric and contextual features without altering the frozen vision‑language model backbone. It introduces a Reweighted Cross‑scale Feature Fusion module to balance shallow and deep features, a Residual Pinwheel‑shaped Gated Convolution module to enhance local geometry in high‑resolution features, and a Residual Convolutional Gated Linear Unit module to suppress background activations and boost region‑of‑interest discriminability. Experiments on COCO‑OVD and LVIS‑OVD show that FocusOVD outperforms state‑of‑the‑art methods, achieving a novel‑category AP of 36.3% on COCO‑OVD and an overall AP of 33.7% on LVIS‑OVD.

By Hanlin Kou, Beiqi Bai, Li Chen, Youjia Jing, Shupan Li, Mingyuan Jiu
llmscomputer-visionmultimodal
More like this →