arXiv Machine Learning
WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image Reconstruction
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 3
Domain shift-robust object detection with GenAI image editing
The paper investigates using diffusion-based generative image editing to improve object detector robustness against domain shifts, specifically camouflaged military vehicle detection. By synthetically adding foliage, netting, and multi‑spectral camouflage to training data with models such as Qwen Image Edit 2509 and Flux.2 Dev, the authors demonstrate significant mAP gains (up to +20.1 for foliage) over detectors trained on uncamouflaged data. LoRA fine‑tuning further boosts performance for the more challenging multi‑spectral camouflage.
arXiv Computer Vision
Oct 12
Advancing Wildlife Conservation through Multimodal Animal Re-Identification with Environmental Metadata
The paper introduces MetaWild, a multimodal animal re-identification dataset that pairs 20,890 images from six species with environmental metadata such as temperature and circadian rhythms. It also proposes the Meta-Feature Adapter (MFA), a lightweight module that integrates this metadata into vision-language models for re-identification tasks. Experiments demonstrate that adding MFA consistently improves re-identification performance over visual-only baselines.
arXiv Computer Vision
Oct 7
Towards benchmarking Western Bluebird detection in the wild
The paper introduces a new benchmark dataset of over 6,000 high‑resolution images for detecting and segmenting Western bluebirds in natural, cluttered scenes. Experiments show that supervised detectors such as Faster R‑CNN and RT‑DETR outperform open‑vocabulary models in zero‑shot settings, though fine‑tuned YOLO‑World can compete. Segmentation results favor Mask R‑CNN for mask quality, while YOLOv8‑Seg offers the best precision and speed. The study also identifies multiple factors—scale, brightness, contrast, clutter, blur, crowding, and session variation—as contributors to detection failures.
arXiv Computer Vision
Sep 21
Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images
The paper introduces an extension of the Decoupled Vision Transformer (DC‑ViT) to handle multi‑channel imaging (MCI) data, where each channel carries a distinct semantic signal. By tokenizing each channel separately and then decoupling intra‑channel from inter‑channel updates, the model preserves channel‑specific features. The authors further enable independent per‑channel masking by solving a linear assignment between retained patches, allowing masked training without restricting visible tokens. Experiments on fluorescence microscopy, imaging mass cytometry, and satellite imaging datasets demonstrate that this approach outperforms the strongest Multi‑Channel Vision Transformer baselines on both classification and dense‑prediction tasks.
arXiv Computer Vision
Sep 30
DeepForestVisionV2: Ecology-Driven Taxonomy Expansion for Camera-Trap Monitoring in African Tropical Forests
arXiv:2606.20223v2 Announce Type: replace Abstract: Camera-trap monitoring in African tropical forests increasingly extends beyond closed-canopy interiors to riverbanks, clearings, and park edges. Am...
arXiv Computer Vision
Oct 9
Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
FreeInpaint is a feed‑forward 3D inpainting framework that reconstructs complete, geometrically consistent scenes directly from unposed multi‑view images with masked regions. It extends a 3D foundation model by propagating masked areas across views, using a Learnable Mask Attention mechanism to maintain reliable cross‑view correspondences and a Support Token Refinement strategy that injects diffusion‑generated auxiliary tokens for high‑fidelity completion. Experiments on diverse datasets show that FreeInpaint delivers superior inpainting quality without requiring pre‑computed camera poses, while maintaining fast inference speed.