arXiv AI
Jun 2
A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
arXiv:2606. 01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task.
Hi-OPD: Hierarchy-Aware Open-Prompt Detection for Remote Sensing Images
Hi-OPD introduces a hierarchy‑aware open‑prompt detector for remote sensing images, addressing inconsistencies that arise when flat open‑prompt training fails to maintain descendant retrieval under ancestor queries. Using a large RS153‑HierOPD dataset with 175,644 images and 3.48M boxes mapped to 153 atomic categories, Hi‑OPD employs hierarchy‑safe negative sampling, path multi‑positive supervision, and one‑way upward consistency to learn ancestor retrieval. The method achieves state‑of‑the‑art AP50 scores on DIOR and DOTA‑v2.0, significantly improves parent and grandparent AP50 metrics, and attains near‑perfect CAR50 across multiple sources.
Related stories
arXiv Computer Vision
Aug 31
WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes
arXiv:2608.28216v1 Announce Type: new Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is ab...
arXiv Computer Vision
Sep 2
SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation
The paper introduces SAM3-LoRA, a parameter‑efficient adaptation of the SAM3 segmentation foundation model using Low‑Rank Adaptation for multi‑class structural defect segmentation. It presents a supervision method that trains the model directly from COCO‑style instance segmentation by using category names as prompts, eliminating the need for prompt templates or learned embeddings. The authors also identify a failure mode where the model responds to any prompt due to positive‑prompt‑only annotations and resolve it with exhaustive hard‑negative prompting, achieving significant improvements in pixel IoU and instance recall on both a tunnel lining dataset and the Structural Defects Dataset.
arXiv AI
Aug 3
Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
arXiv Machine Learning
Jul 31
When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment
arXiv:2607. 27530v1 Announce Type: new Abstract: Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a class label or molecular property.
arXiv Computer Vision
Oct 2
Subtoken Vision Transformer for Fine-grained Recognition
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
arXiv AI
Aug 26
OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses
The paper introduces D3-Omni, a balanced and decoupled benchmark designed to diagnose fine‑grained multimodal understanding in OmniJudges that evaluate text‑to‑image, text‑to‑video, and text‑to‑speech generation. D3-Omni covers 53 orthogonal binary dimensions across 10,671 samples, using fixed positive seeds and controlled prompt rewriting to generate negatives, thereby ensuring each error can be attributed to a single capability. The benchmark’s dual‑balanced, decoupled, and dynamic design achieves near 1:1 per‑dimension parity and a uniform total‑score distribution, revealing that strong OmniJudges often miss modality‑related failures and treat distinct attributes as a single decision, masking systematic blind spots.
arXiv Computer Vision
Aug 25
AcroMELD: Recovering Interactive PDF Forms with Structure-Aware Graph Set Transformers
arXiv:2608.22338v1 Announce Type: new Abstract: Interactive PDF form fields are often absent from documents that visually resemble forms, leaving users unable to enter data without printing or extern...
arXiv AI
Aug 11
SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision
arXiv:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.
arXiv Computer Vision
Sep 24
SGDet3D++: Geometry-Grounded Semantics for 4D Radar and Camera 3D Object Detection
SGDet3D++ introduces a geometry‑grounded approach to 4D radar‑camera 3D object detection by explicitly conditioning evidence on evolving object hypotheses. It employs Anchor‑Grounded Semantic Retrieval, Geometry‑Consistent Anchor Refinement, and Doppler‑Verified Correspondence to filter and align semantic, geometric, and temporal cues before updating queries. The method achieves significant performance gains on OmniHD‑Scenes, ManTruckScenes, and TJ4DRadSet, with detailed ablations showing improvements in occlusion handling, target‑return purity, and motion consistency.
arXiv Machine Learning
Aug 27
CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifact
CropCop is a closed‑set plant‑health recognition system covering 120 operational classes, built from a rigorously audited dataset of 109,107 images after removing 3,233 duplicate relationships. The model, based on a fine‑tuned DINOv3 ConvNeXt‑Tiny, achieves 98.51% accuracy and 96.87% macro‑F1 on a locked internal test, while a quantised MobileNetV4 variant reaches 98.46% accuracy and 96.23% macro‑F1 in a 22.60 MiB runtime artifact. Validation‑only post‑training quantisation and a compact ExecuTorch/XNNPACK PTE ensure high fidelity between the trained model and its deployed form, with minimal decision changes between the INT8 graph and the final artifact.
Hugging Face Trending Papers
Jun 29
UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction
Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few-shot transfer regime, the key challenge is to estimate an episode-specific boundary for an unseen target category from a small support set.