OD3 presents an optimization-free dataset distillation framework for object detection that reports new state-of-the-art accuracy on COCO and VOC at compression ratios from 0.25% to 5%.
super hub
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
35 Pith papers cite this work, alongside 18,238 external citations. Polarity classification is still indexing.
35
Pith papers citing it
18.2k
external citations · Pith
abstract
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.
hub tools
citation-role summary
background 2
dataset 1
method 1
citation-polarity summary
representative citing papers
A dual-stream vision transformer with modality-aware gated exchange and bidirectional token exchange fuses RGB, thermal, and event data to improve UAV vehicle detection over dual-modal baselines on a new 10,489-frame dataset.
GraspIT provides ~316k annotated RGBD frames with ~2.3M slip-test-validated 6-DoF grasp candidates and a bidirectional sim-to-real registration pipeline, all released as open-source Docker containers.
RefDiffNet is a lightweight input enhancement block that uses reference image comparison to expose PCB defects, delivering up to 18% relative mAP50:95 gains across YOLO, RT-DETR, and Faster R-CNN detectors with 0.004-0.005M extra parameters.
Presents an end-to-end multitask CNN with FPN, dynamic RoI pooling, and convolutional attention for simultaneous lexicon-free text localization and recognition in complex images.
Controlled counterfactual perturbations reveal no correlation between embedding cosine similarity and approximation behavior in two visual grounding models.
TriPatch generates transferable physical adversarial patches via multi-stage triplet loss, appearance consistency, and data augmentation to achieve higher attack success rates on pedestrian detectors than prior methods.
PASTA enables patch-agnostic backdoor activation in ViTs via multi-location trigger insertion during training and bi-level optimization, achieving 99.13% average attack success with large gains in visual/attention stealthiness and defense robustness.
AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
DroneScan-YOLO reaches 55.3% mAP@50 and 35.6% mAP@50-95 on VisDrone2019-DET by combining 1280x1280 input, RPA-Block pruning, MSFD stride-4 branch, and SAL-NWD loss, beating YOLOv8s by 16.6 and 12.3 points with only 4.1% more parameters.
VLM-based harmonization of inconsistent annotations across two document layout corpora raises detection F-score from 0.860 to 0.883 and table TEDS from 0.750 to 0.814 while tightening embedding clusters.
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
Presents RT-DocLayout, a 33M-parameter end-to-end model extending RT-DETR that unifies layout classification, detection, segmentation, and reading-order prediction at 132.1 FPS with claimed SOTA results on public benchmarks.
VFACamou uses UV-volume rendering and a diffusion-based texture generator with illumination consistency to produce environment-adaptive adversarial camouflage for physical evasion.
A CNN detects 19,685 LAEs at z=2-3.5 in DESI DR1 spectra with 95% purity and completeness.
XAI analysis identifies high visual similarity across colony cardinality classes as the primary limit on MicrobiaNet performance in bacterial colony counting, revising prior model assessments.
WSA-Net uses partial convolutions, heterogeneous grouping attention, geometric reconstruction, and context anchoring to enhance low-SCR hyperbolic signatures in GPR data, reaching 0.6958 mAP@0.5 at 164 FPS with 2.412M parameters on the RTST dataset.
Mask-conditioned LDM generates synthetic TEM defect image-mask pairs that augment small experimental sets and produce up to 0.02 gain in harmonic-mean F1 for combined detection and classification with Mask R-CNN.
Develops and benchmarks a siamese latent-representation system for object-level building damage assessment directly onboard Earth observation satellites.
Three lightweight VVC profiles for feature coding achieve up to 2.96% BD-Rate gain and 95.6% encoding speedup while preserving downstream task accuracy under the MPEG-AI FCM framework.
GarmNet jointly localizes garments and detects grasp landmarks on the CloPeMa dataset, reducing localization error by 24.7% when landmark detection is included.
A two-stage weakly supervised pipeline pretrains on auto-generated school labels from sparse points and fine-tunes on only 50 manual examples to achieve strong detection performance in aerial imagery.
A multi-dataset cross-domain knowledge distillation approach improves unified performance on medical image segmentation, classification, and detection by transferring domain-invariant features from a joint teacher model to task-specific students.
KAYRA packages a cascade of EfficientNet-B5 + U-Net, Mask R-CNN, and ResNet-18 models into a microservice architecture that supports both cloud and on-premise deployment and reaches 98.91% segmentation accuracy in a pilot test on 459 chromosomes.
citing papers explorer
-
Virtual KITTI 2
Virtual KITTI 2 supplies synthetic clones of real KITTI driving sequences with added weather and camera variants and multi-modal ground-truth annotations for autonomous driving vision research.