Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2608.30281v1 Announce Type: new Abstract: Class-Incremental Semantic Segmentation (CISS) is fundamentally challenged by catastrophic forgetting and background shift, where learning new concepts...
MANTLE is a multi‑task adaptive network designed for planetary perception, featuring a shared DINOv2 backbone with separate heads for landform classification and boulder segmentation. Trained on HiRISE and MSL imagery, it achieved 92.56% accuracy on seven Martian terrain classes and a 0.753 IoU for boulder segmentation, with strong cross‑sol generalization. The framework follows the Modular Uplink Principle, allowing lightweight task‑specific heads to be trained on Earth and uplinked to the rover without retraining the core model.
The study examines how different two‑dimensional projections of spherical 360‑degree video affect end‑to‑end neural compression. Seven JVET‑360Lib formats were evaluated using a scale‑space flow model on standard test sequences, with performance measured by PSNR, spherical PSNR, weighted spherical PSNR, and BD‑rate. Results show that equirectangular and padded equirectangular projections yield the best compression efficiency with the neural model, while cubemap‑based formats excel with conventional HM‑16.16 codecs, highlighting that projection choice is codec‑dependent.
GramLoop is a training‑free framework that enhances frozen DINOv3 dense‑prediction models under distribution shift by adding inference computation within the visual backbone. It replays a short transformer window and uses final‑layer cosine‑Gram consistency to control each replay, propagating proposals through the frozen suffix and accepting them via a patchwise gate. Across object detection and semantic segmentation tasks, GramLoop improves performance on all five shifted benchmarks, notably raising COCO‑O mAP by +0.252 and Effective Robustness by +0.250 while maintaining clean ADE20K accuracy.
The paper studies how open‑vocabulary segmentation models perform on UAV footage, focusing on temporal consistency of predictions. By linking frame‑wise outputs to persistent 3D voxels via metric fusion, the authors propose a voxel‑level evaluation that measures final agreement, Semantic Belief Drift, Observation Persistence, and uncertainty. Experiments on UAVid‑3D show that high overall agreement can mask instability when observations are sparse, and that persistence‑stratified analysis reveals greater disagreement for recurrent voxels while belief drift reduces with more evidence.
Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding introduces SPAR, a joint semantic‑geometric encoding architecture that isolates transient dynamic noise before latent space aggregation. The method couples motion estimation with multi‑view visual and semantic learning in a dynamic‑region‑aware end‑to‑end training paradigm, enabling the network to resolve motion conflicts and produce temporally stable scene representations. Experiments on the D‑RE10K benchmark show state‑of‑the‑art performance, achieving high PSNR values for novel view synthesis and an 88.5% mIoU for motion mask prediction in a self‑supervised setting.
RLG-TPV introduces a multimodal Tri-Perspective View framework that fuses camera, radar, and training‑time LiDAR data for 3D object detection. It uses radar and LiDAR to guide a ray‑deformable attention lift, refining depth distributions and providing geometric supervision for side and front planes, while radar cross‑section awareness spreads evidence spatially. On nuScenes, the method attains 0.4981 mAP and 0.5959 NDS, improving orientation and velocity accuracy by about 32 % and 31 % over the CRN baseline.
The paper investigates continual machine unlearning, where models must forget data over time. It identifies a fundamental issue called plasticity collapse, where successive unlearning requests cause geometric constraints that saturate parameter space, leading to two failure modes: forward failure (reduced forgetting quality) and backward failure (re‑memorization). Experiments across architectures and datasets confirm that plasticity collapse is a pervasive problem in continual unlearning.
arXiv:2608.30633v1 Announce Type: cross Abstract: Timely post-disaster building damage assessment from satellite imagery is a critical engineering decision support task, yet it remains constrained by...
The paper introduces AraSEG, a new Arabic sentence segmentation corpus covering eight genres and diverse punctuation and document structures. Experiments using AraSEG evaluate large language models, lightweight encoders, and dependency parser-based models, revealing that lightweight encoders and parser-based models outperform LLMs under the most challenging conditions. The study also shows that increasing training data size and genre diversity eventually saturates performance, that cross‑genre generalization remains difficult, and that accurate sentence segmentation significantly improves downstream dependency parsing.
arXiv:2608.30616v1 Announce Type: new Abstract: Pottery is a primary source for reconstructing the chronological and economic dimensions of past societies. Archaeologists often document ceramic finds...
arXiv:2604.12335v2 Announce Type: replace-cross Abstract: Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as...
The paper introduces a composition‑aware pretraining framework for geospatial foundation models that explicitly encodes fractional land‑cover mixtures as histogram targets for each satellite image cell. By using Earth Mover’s Distance to distill these composition targets into a 36.8 M‑parameter backbone, the authors demonstrate significant improvements on region‑level tasks such as zero‑shot image retrieval and scene classification, while maintaining competitive performance on fine‑grained tasks like segmentation and object detection. The method outperforms larger models (SatMAE and Prithvi‑EO‑2.0) and achieves a 55.6 % relative boost on the ForestNet‑12 dataset, evidencing the benefit of explicit composition modeling.
arXiv:2608.30870v1 Announce Type: new Abstract: Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature d...
arXiv:2608.30895v1 Announce Type: new Abstract: Performance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model conf...
arXiv:2608.28595v1 Announce Type: new Abstract: Biomedical NLP pipelines routinely presuppose clean input text, yet large-scale corpora assembled through automated PDF parsing harbour pervasive OCR-l...
arXiv:2608.30129v1 Announce Type: new Abstract: This work presents $\textbf{Lapis}$, a $\textbf{l}$inear-$\textbf{a}$ttention-based $\textbf{pi}$xel-$\textbf{s}$pace generative framework that achieve...
arXiv:2608.29852v1 Announce Type: new Abstract: Automated maritime surveillance from satellite and aerial imagery requires large, precisely annotated datasets, which remain scarce for the instance-se...
arXiv:2608.29793v1 Announce Type: new Abstract: Generating realistic 3D city environments from remote sensing data is important for simulation, urban planning, and mixed reality, yet existing point c...
arXiv:2608.29891v1 Announce Type: new Abstract: Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approac...