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.
arXiv:2608.20621v1 Announce Type: new Abstract: Text-guided zero-shot object counters excel at spatial localization but categorize poorly on novel or fine-grained classes: natural language is too coa...
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...
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.
arXiv:2610.08379v1 Announce Type: new Abstract: Visual counting is commonly formulated as counting a single specified target, with a model receiving an image-specific exemplar, text query, or target...
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.
arXiv:2605. 29539v2 Announce Type: replace-cross Abstract: Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD).
arXiv:2610.09502v1 Announce Type: new Abstract: Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with...
arXiv:2609.38362v1 Announce Type: new Abstract: Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining dis...
The paper introduces PromptCCZSL, a framework that enables vision‑language models to continually learn new attributes, objects, and their unique compositions while avoiding forgetting. It uses a frozen VLM backbone with prompt‑based techniques, recency‑weighted multi‑teacher distillation, and several loss functions (CAL, OPL, IDL) to maintain prior knowledge and promote diverse, distinct embeddings. Experiments on UT‑Zappos and C‑GQA show significant performance gains over existing VLM‑based and non‑VLM baselines, establishing a new benchmark for continual compositional zero‑shot learning.
arXiv:2607. 00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification.
arXiv:2609.31356v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as ideali...
arXiv:2609.37096v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) consistently struggle with fine-grained visual counting, yet the underlying causes remain poorly understood. I...