Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2609.09634v1 Announce Type: new Abstract: Large networks and ensembles often lead medical image segmentation challenges, but their storage and inference demands complicate deployment. We presen...
The paper presents a family of tunable lifting schemes for biorthogonal wavelet filter banks, introducing three strategies: low‑pass tuning, high‑pass tuning, and a sequential scheme that jointly adapts both branches. These designs use a lattice‑based lifting structure to ensure invertibility and stability for any parameter values. The authors integrated the schemes into a ResNet‑18 backbone and evaluated them on image classification (DTD) and anomaly detection (MVTec‑AD and KRC102S), reporting consistent performance improvements across all tasks.
The paper presents a solution for the UCF UrbanTwin LUMPI Track in the Sim-to-Real LiDAR Challenge, where a detector trained solely on synthetic data must perform on real LiDAR frames. The approach tackles the Sim2Real gap through data alignment, diversified sampling, augmentation, and specialized detectors, followed by class-aware fusion and calibration techniques. The final submission achieved a Combined Score of 0.4692, a Detection Score of 0.1797, a Realism Score of 0.9035, and a 3D mAP@0.5 of 0.1258.
The paper investigates how the choice of segmentation affects LIME explanations for document image classification. It compares standard superpixel methods (Quickshift and SLIC) with document-aware segmentations based on OCR bounding boxes and regular grids on the RVL-CDIP dataset. The study finds that document-aware segmentations yield more consistent, correct, and locally faithful explanations, require fewer perturbations, and reveal shortcut behaviors tied to document identification codes that superpixel-based LIME often hides.
arXiv:2609.06826v1 Announce Type: new Abstract: This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is int...
The paper introduces a structure‑aware federated learning framework for segmenting catheters and guidewires in X‑ray fluoroscopy. It presents a new benchmark dataset, CathAction, and a shape‑sensitive loss that improves segmentation accuracy. The approach extends to federated learning, adding projected gradient descent for adversarial optimization, and includes a diffusion‑based synthetic data generator that boosts performance under data scarcity.
Vague2Detect is a hybrid pipeline that improves object detection for ambiguous prompts by combining a fine‑tuned Sentence‑BERT to retrieve candidates from a structured household knowledge base, YOLO‑World to verify their presence in images, and a GPT‑3.5‑turbo fallback to generate new candidate descriptions when prompts fall outside the knowledge base. On a benchmark of household scenes, Vague2Detect raises the vague prompt success rate from 32% (YOLO‑World alone) to 61% with high precision, and up to 85% when the GPT fallback is used.
arXiv:2605.27156v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail do...
arXiv:2609.10334v1 Announce Type: new Abstract: This paper addresses the issue of supervised classification in the context of hyperspectral satellite images. It deals with two fundamental aspects: di...
The paper describes a system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. It combines a small 4‑B‑parameter VLM fine‑tuned as a per‑token classifier that uses a two‑token feature from its hidden states with a large ~400‑B zero‑shot VLM judge at prediction time, both leveraging OCR of visible in‑image text. Using synthetic hallucination data from the large model for ensemble diversity and validation‑based selection of feature layer, training data, and OCR grounding, the entry achieved competitive results across multiple languages.
arXiv:2508.13977v4 Announce Type: replace Abstract: Depth estimation is a fundamental component of spatial perception for autonomous driving and other unmanned systems operating in open urban environ...
AudioFuse is a hybrid architecture that jointly learns from spectrograms and raw waveforms to classify phonocardiograms. It combines a wide-and-shallow Vision Transformer for spectral features with a shallow 1D CNN for temporal waveforms, reducing overfitting while capturing complementary information. On the PhysioNet 2016 dataset, AudioFuse achieves a state‑of‑the‑art ROC‑AUC of 0.8608 and shows superior robustness to domain shift on the PASCAL dataset, outperforming both spectrogram‑only and waveform‑only baselines.
arXiv:2609.07004v2 Announce Type: replace Abstract: Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches...
GoDeep is an annotation‑free method for open‑vocabulary 3D scene understanding that uses a vision‑language model solely as a translator to generate structured, entity‑level descriptions of each image. These descriptions are projected and aggregated in a language‑only embedding space, eliminating the need for a 3D training corpus or domain‑specific encoder. The approach achieves competitive performance on ScanNet++ and a cultural heritage benchmark, accurately localizes out‑of‑vocabulary objects, and offers explainable, point‑level predictions.
TriCCOT is a tri-part architecture designed for onboard space object detection that balances computational efficiency with robust performance. It combines a convolutional region proposal network, a conformal prediction stage that enlarges bounding boxes with distribution‑free probabilistic coverage, and Aper‑GATES—a hardware‑friendly attention‑based classifier that replaces standard transformer operations with convolutional projections and gating. Experiments on DIOR and VDVRaw datasets show competitive detection accuracy and improved robustness to blur and noise, and the model was fully deployed on a Xilinx Versal VCK190 FPGA without altering the underlying DPU architecture.
WSPolypNet is a weakly supervised framework that localizes polyps in colonoscopy videos using only video-level labels, avoiding costly frame-level annotations. It employs a 3D CNN to generate class activation maps, enhances them with a multi-view strategy, and refines the results with MedSAM2 segmentation. The method achieves higher CorLoc scores—up to 47.80% at IoU 0.3—and a recall of 94.51%, especially improving detection of small polyps.
The paper introduces a multi‑modal late‑fusion perception pipeline for object detection and tracking in autonomous racing. It combines independent detections from cameras, LiDARs, and RADARs to produce timely and robust state estimates of surrounding vehicles. The tracking framework compensates for detection delays and incorporates vehicle dynamics and track layout knowledge, and its effectiveness is confirmed through real‑world experiments in diverse critical scenarios.
The paper introduces the Geo-Context Guided Visual Transformer, a model that augments remote sensing image analysis with geospatial embeddings and an asymmetric attention module. By converting heterogeneous geospatial variables into patch-aligned representations and assigning geospatial roles to attention heads, the approach improves disease prevalence prediction over existing vision-language and graph-based baselines. Ablation and visualization studies demonstrate its effectiveness and interpretability for health-related remote sensing tasks, especially when comprehensive geospatial data are scarce.
The paper introduces Emo-DVS, a large-scale, multimodal dataset combining event camera, audio, and text data for emotion recognition, designed to mitigate privacy concerns associated with RGB cameras. It proposes the Information‑Guided Gated Fusion (IGF) framework, which pre‑trains an event encoder on the dataset’s FAU subset, adaptively gates modalities to reduce noise, and aligns cross‑modal representations via mutual information maximization. Experiments show that IGF outperforms existing methods on this challenging tri‑modal benchmark.
The paper presents a unified taxonomy that classifies machine‑learning and artificial‑intelligence applications according to mathematical programming paradigms such as linear, quadratic, mixed‑integer, conic, bilevel, and others. It standardizes notation, identifies key inputs, decision variables, and principal formulations for each application, and discusses structural properties, solution strategies, and limitations. The authors compare tractability, relaxation quality, decomposition, approximation guarantees, and scalability across paradigms, emphasizing that mathematical programming serves as a disciplined interface between predictions and constrained decisions rather than a universal modeling claim.