Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2510.17198v2 Announce Type: replace Abstract: Riverbank erosion is a serious environmental problem in Bangladesh, causing land loss, damage to infrastructure, and displacement of local communit...
The paper explores using denoising diffusion generative models as plug‑and‑play priors for high‑dimensional inference problems. By combining a pre‑trained diffusion prior with a differentiable auxiliary constraint, the authors enable approximate inference through iterative differentiation across multiple noisy versions of the data. This framework opens possibilities for conditional generation, image segmentation, and novel combinatorial optimization algorithms.
The study presents an IoT-enabled acoustic monitoring system that uses a Raspberry Pi and high‑sensitivity microphone to capture audio from tea trunks, creating a dataset of 2,000 ten‑second samples (1,000 healthy, 1,000 infested). A CNN trained on Fourier‑derived spectrograms achieved 81.5% accuracy in classifying Postelectrotermes militaris infestations, and a weighted severity model combined CNN probability, acoustic amplitude, and proximity of infested plants to generate quantitative severity scores and geospatial maps. Field trials in Pundaluoya confirmed the system’s feasibility amid realistic environmental noise, offering plantation managers tools to identify high‑risk areas and prioritize inspections.
The paper introduces an anatomy-aware, promptable segmentation model for whole-body lesion detection in FDG and PSMA PET/CT scans, tailored for the AUTOPET V challenge. The approach builds on nnU-Net, employing a two-stage training process: an initial pre-training phase for strong baseline segmentation and an online interactive phase that refines predictions using scribble prompts. Anatomical context is integrated via organ supervision with a shared head predicting both lesions and organs, reducing false positives, while a tracer classifier directs studies to either a combined FDG+PSMA model or a PSMA-specific model. Cross-validation results show that organ-supervised training yields the most stable performance, the interactive stage consistently improves Dice scores, and PSMA-specific training delivers the best tracer-wise results.
The paper examines OCR adaptation for low‑resource languages, noting that fine‑tuning often hits a performance ceiling in data‑scarce settings. It identifies that lower layers of language‑specific models learn redundant features while higher layers capture script nuances, leading to a structural inefficiency. To address this, the authors propose PSMC, a framework that pre‑trains a base model, specializes it per language, merges the experts via task arithmetic, and co‑trains a unified multilingual backbone, achieving about a 2% improvement in Word Recognition Rate across 10 Indian scripts without adding parameters.
HyperVision introduces the first ground‑based hyperspectral pre‑trained backbone, addressing challenges of varying spectral configurations, limited annotations, and dataset diversity. It employs a channel‑adaptive dynamic embedding to unify heterogeneous inputs, a multi‑source pseudo‑labeling strategy combining SAM2 spatial cues with HyperFree spectral details, and cross‑modal knowledge distillation from a pre‑trained RGB vision model. Trained on 15k images from 26 datasets, HyperVision achieves significant improvements—up to 16.3% relative gain in hyperspectral semantic segmentation, 2.1% in object tracking AUC, and 35.5% reduction in salient object detection MAE—while requiring only head‑only adaptation.
This paper presents an end-to-end, agent-driven pipeline for the LoD3 reconstruction of facade openings in 3D city models, producing directly usable CityGML-conform outputs. In contrast to existing ap...
Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes the object within a target image, the latter retr...
The article discusses how noisy text—stemming from user typos, rapid transcription errors, and OCR character mistakes—poses challenges for Retrieval-Augmented Generation (RAG) systems. It explains that traditional spell-checking only addresses one type of error, while embeddings are needed to handle the remaining noise. The piece highlights the need for more robust solutions in enterprise document intelligence.
The article argues that Retrieval-Augmented Generation (RAG) is only one tool in NLP, and many real-world problems—such as request classification, free‑text matching, table reading, and OCR noise cleaning—are better served by simpler, cheaper techniques. It emphasizes the importance of selecting the appropriate method for each task and highlights the engineering challenge of knowing which technique to apply.
The paper introduces MedREAL, a unified framework that aligns linguistic reasoning with spatial grounding for medical visual question answering and segmentation. MedREAL employs Seg Anchored Reasoning Pooling (SARP) to extract semantic evidence from segmentation tokens and a Reasoning-to-Visual (R2V) fusion mechanism to integrate these features into a segmentation pipeline. Using the newly created MedRAVS-13K dataset, MedREAL achieves superior performance, reporting 68.49% gIoU and 70.47% cIoU, and generates evidence masks that consistently match textual diagnoses.
The paper introduces an importance‑scoring metric for multi‑head transformer attention heads applied to tabular data, a domain where transformers have been less studied. Experiments on 40 diverse tabular datasets show that removing heads with the lowest importance scores has minimal impact on performance, while removing the most important head first causes the largest drop. The study finds that important heads are distributed across layers and vary significantly across different tabular schemas, suggesting that the proposed score can help reduce redundancy and improve transformer efficiency.
DINOcular is a self‑supervised framework that learns joint visuospatial representations from RGB‑D observations. It fuses depth‑derived geometric priors with a visual backbone using inter‑patch and intra‑patch fusion, allowing the model to encode both appearance and spatial structure efficiently. The resulting representation improves 3D awareness on multiple geometry benchmarks while staying competitive on standard RGB‑D semantic segmentation tasks.
This systematic literature review examines 97 studies on optical character recognition (OCR) from 2015 to 2025, tracing the evolution of AI models, application domains, data types, and linguistic coverage. It identifies key OCR models, evaluates their performance, strengths, and limitations, and highlights unresolved challenges such as limited resources for underrepresented languages, high variability in handwritten text, and constraints in real‑time applications. The review proposes promising approaches—including self‑supervised learning, multimodal AI, AutoML, AI‑assisted postprocessing, TinyML, and joint corpora creation—to enhance OCR accuracy and address these challenges for industrial use.
SOCO is a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. It also includes keypoint language descriptions, enabling evaluation of large vision‑language models and their fine‑grained part‑level understanding. Experiments show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories, LVLMs excel at text‑prompted part localization but lag in visual‑reference matching, and correspondence performance predicts dense downstream tasks more strongly than ImageNet classification.
The paper introduces MILO, a framework that uses Large Reconstruction Models (LRMs) to reconstruct detailed 3D human‑object interactions from a single image. By treating the LRM mesh as a geometric scaffold, MILO segments it into human and object parts, fits a parametric body model to the human component, and optionally aligns an object template to the object component. The approach achieves higher reconstruction accuracy than existing baselines across multiple benchmarks and interaction scenarios.
SSMB is a self‑supervised keypoint detector designed for motion‑blurred images that does not rely on handcrafted detectors or external pseudo‑labels. It introduces a Local Discriminability Enhancement module to recover fine‑grained local detail after global feature mixing, and is trained in two stages: geometric pretraining on synthetic shapes and blur‑aware training on real sharp‑blur pairs using a multi‑component self‑supervised objective. Extensive experiments show that SSMB outperforms both supervised and self‑supervised baselines on keypoint detection, image matching, relative pose estimation, and visual localization under motion blur, achieving state‑of‑the‑art performance.
UFO-DETR is an end‑to‑end object detection framework designed for UAV imagery, addressing challenges such as scale variation, dense distribution, and the prevalence of tiny targets. It employs an LSKNet backbone to optimize receptive fields and reduce parameters, integrates DAttention and AIFI modules for flexible multi‑scale spatial modeling, and introduces a DynFreq‑C3 module that enhances small target detection via cross‑space frequency feature enhancement. Experiments demonstrate that UFO‑DETR outperforms RT‑DETR‑L in detection accuracy while improving computational efficiency, making it suitable for UAV edge computing.
The paper introduces DPA-I2P, a depth-guided projective alignment method for image-to-point-cloud registration in autonomous driving. It employs Ray-Conditioned Metric Depth Encoding and Projection-Consistent Vision Lifting to align depth and visual cues geometrically, and uses Cross-Modal Query Pruning to enhance matching stability. Experiments on KITTI and nuScenes show significant reductions in rotation and translation errors compared to existing implicit baselines.
The paper introduces DOD-SA, a framework for infrared-visible object detection that uses only single-modality annotations. It employs a Collaborative Teacher-Student Network with a single-modality branch and a dual-modality decoupled branch to transfer knowledge across modalities, and a Progressive and Self‑Tuning Training Strategy to refine pseudo‑labels. A Pseudo Label Assigner is also designed to align labels between modalities during training.