UniTopo unifies lane detection and topology reasoning into a single perception model, outperforming prior methods on OpenLane-V2 benchmarks with TOP_ll scores of 30.1% and 31.8%.
hub
Deformable DETR: Deformable Transformers for End-to-End Object Detection
44 Pith papers cite this work. Polarity classification is still indexing.
44
Pith papers citing it
abstract
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.
hub tools
claims ledger
- abstract DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive e
co-cited works
representative citing papers
Introduces OW-SED paradigm and WOOT transformer framework to detect known sounds, identify unseen events, and incrementally learn in open audio environments.
A YOLO26 model trained on four leaf segmentation datasets reaches 83.9% mean mAP50-95 on their test sets but only 40.2% on a new 23-species benchmark, revealing substantial cross-domain generalization gaps.
ConFusion reaches 59.1 mAP and 65.6 NDS on nuScenes validation by combining heterogeneous queries with QMix cross-attention and QSwap feature exchange.
URoPE is a parameter-free relative position embedding for transformers that works across arbitrary geometric spaces by ray sampling and projection, yielding consistent gains on novel view synthesis, 3D detection, tracking, and depth estimation.
CoEvoer is a new cross-dependency transformer framework for upper-body expressive human pose and shape estimation that achieves state-of-the-art performance by enabling mutual enhancement between body parts.
HELP uses heatmap-guided positional embeddings and a gradient mask to suppress background noise in queries, enabling efficient small-object detection with fewer decoder layers and parameters.
Topology-preserving synthetic P&IDs generated by seeding from real drawings enable models trained solely on synthetics to achieve 63.8% edge mAP on real P&ID benchmarks, closing most of the gap to real-data training.
The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.
YUV20K is a complexity-driven VCOD benchmark with 24k annotated frames, paired with a model using Motion Feature Stabilization via semantic primitives and Trajectory-Aware Alignment via deformable sampling that outperforms prior methods.
DinoRADE reports a radar-centered multi-class detection pipeline that fuses dense radar tensors with DINOv3 features via deformable attention and outperforms prior radar-camera methods by 12.1% on the K-Radar dataset across weather conditions.
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
WUTDet is a 100K-image ship detection dataset with benchmarks indicating Transformer models outperform CNN and Mamba architectures in accuracy and small-object detection for complex maritime environments.
A probabilistic unfolding network with stable likelihood projection and dual-domain Mamba achieves state-of-the-art reconstruction in quantized compressive sensing.
A new framework combines self-attention on the Oblique manifold with bidirectional geodesic cross-attention on the Lorentz hyperboloid to improve both localization accuracy and descriptive coherence in 3D dense captioning.
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
Non-overlapping RGB-T adversarial patterns on clothing, optimized with spatial discrete-continuous optimization, achieve high attack success rates against multiple RGB-T detector fusion architectures in both digital and physical evaluations.
InterMesh improves multi-person human mesh recovery accuracy by explicitly enriching DETR-style queries with structured interaction semantics from a human-object detector.
FUN is an end-to-end Focal U-Net that performs joint hyperspectral image reconstruction and object detection via multi-task learning with focal modulation, achieving SOTA results with 40% fewer parameters and a new 363-image dataset.
ViCrop-Det uses spatial attention entropy from the decoder to dynamically crop and refine small-object regions in transformer detectors during inference.
GateMOT proposes Q-Gated Attention to enable linear-complexity, spatially aware attention for state-of-the-art dense object tracking on benchmarks like BEE24.
OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.
WSRVOS enables referring video object segmentation with text-only supervision by combining MLLM-based expression augmentation, multimodal feature interaction, pseudo-mask fusion, and temporal ranking constraints.
HiProto uses hierarchical prototypes with RPC-Loss, PR-Loss, and SPLGS to deliver competitive, interpretable object detection on low-quality datasets like ExDark and RTTS.
citing papers explorer
-
Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning
UniTopo unifies lane detection and topology reasoning into a single perception model, outperforming prior methods on OpenLane-V2 benchmarks with TOP_ll scores of 30.1% and 31.8%.
-
Towards Open World Sound Event Detection
Introduces OW-SED paradigm and WOOT transformer framework to detect known sounds, identify unseen events, and incrementally learn in open audio environments.
-
ReLeaf: Benchmarking Leaf Segmentation across Domains and Species
A YOLO26 model trained on four leaf segmentation datasets reaches 83.9% mean mAP50-95 on their test sets but only 40.2% on a new 23-species benchmark, revealing substantial cross-domain generalization gaps.
-
Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusion
ConFusion reaches 59.1 mAP and 65.6 NDS on nuScenes validation by combining heterogeneous queries with QMix cross-attention and QSwap feature exchange.
-
URoPE: Universal Relative Position Embedding across Geometric Spaces
URoPE is a parameter-free relative position embedding for transformers that works across arbitrary geometric spaces by ray sampling and projection, yielding consistent gains on novel view synthesis, 3D detection, tracking, and depth estimation.
-
Chatting about Upper-Body Expressive Human Pose and Shape Estimation
CoEvoer is a new cross-dependency transformer framework for upper-body expressive human pose and shape estimation that achieves state-of-the-art performance by enabling mutual enhancement between body parts.
-
Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
HELP uses heatmap-guided positional embeddings and a gradient mask to suppress background noise in queries, enabling efficient small-object detection with fewer decoder layers and parameters.
-
SynthPID: P&ID digitization from Topology-Preserving Synthetic Data
Topology-preserving synthetic P&IDs generated by seeding from real drawings enable models trained solely on synthetics to achieve 63.8% edge mAP on real P&ID benchmarks, closing most of the gap to real-data training.
-
Online Reasoning Video Object Segmentation
The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.
-
YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detection
YUV20K is a complexity-driven VCOD benchmark with 24k annotated frames, paired with a model using Motion Feature Stabilization via semantic primitives and Trajectory-Aware Alignment via deformable sampling that outperforms prior methods.
-
DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather
DinoRADE reports a radar-centered multi-class detection pipeline that fuses dense radar tensors with DINOv3 features via deformable attention and outperforms prior radar-camera methods by 12.1% on the K-Radar dataset across weather conditions.
-
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
-
WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects
WUTDet is a 100K-image ship detection dataset with benchmarks indicating Transformer models outperform CNN and Mamba architectures in accuracy and small-object detection for complex maritime environments.
-
Deep Probabilistic Unfolding for Quantized Compressive Sensing
A probabilistic unfolding network with stable likelihood projection and dual-domain Mamba achieves state-of-the-art reconstruction in quantized compressive sensing.
-
Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding
A new framework combines self-attention on the Oblique manifold with bidirectional geodesic cross-attention on the Lorentz hyperboloid to improve both localization accuracy and descriptive coherence in 3D dense captioning.
-
A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
-
Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
Non-overlapping RGB-T adversarial patterns on clothing, optimized with spatial discrete-continuous optimization, achieve high attack success rates against multiple RGB-T detector fusion architectures in both digital and physical evaluations.
-
InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery
InterMesh improves multi-person human mesh recovery accuracy by explicitly enriching DETR-style queries with structured interaction semantics from a human-object detector.
-
FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging
FUN is an end-to-end Focal U-Net that performs joint hyperspectral image reconstruction and object detection via multi-task learning with focal modulation, achieving SOTA results with 40% fewer parameters and a new 363-image dataset.
-
ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection
ViCrop-Det uses spatial attention entropy from the decoder to dynamically crop and refine small-object regions in transformer detectors during inference.
-
GateMOT: Q-Gated Attention for Dense Object Tracking
GateMOT proposes Q-Gated Attention to enable linear-complexity, spatially aware attention for state-of-the-art dense object tracking on benchmarks like BEE24.
-
OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.
-
Weakly-Supervised Referring Video Object Segmentation through Text Supervision
WSRVOS enables referring video object segmentation with text-only supervision by combining MLLM-based expression augmentation, multimodal feature interaction, pseudo-mask fusion, and temporal ranking constraints.
-
HiProto: Hierarchical Prototype Learning for Interpretable Object Detection Under Low-quality Conditions
HiProto uses hierarchical prototypes with RPC-Loss, PR-Loss, and SPLGS to deliver competitive, interpretable object detection on low-quality datasets like ExDark and RTTS.
-
Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization
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.
-
Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection
Telescope uses learnable hyperbolic foveation to deliver a 76% relative mAP gain (0.185 to 0.326) for objects beyond 250 meters while keeping overhead low.
-
Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation
GCNV-Net achieves state-of-the-art accuracy on multiple 3D medical segmentation benchmarks while cutting FLOPs by 56% and inference latency by 68% through dynamic nonvoid voxelization and geometric attention.
-
PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
PET-DINO unifies visual and text prompts in Grounding DINO via an alignment-friendly generation module and prompt-enriched training strategies to improve zero-shot open-set object detection.
-
YOLOv12: Attention-Centric Real-Time Object Detectors
YOLOv12 is a new attention-based real-time object detector that reports higher accuracy than YOLOv10, YOLOv11, and RT-DETR variants at comparable or better speed and efficiency.
-
Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation
HeroCrystal achieves 33.4% mAP on cross-domain multi-camera object detection by combining one-shot diffusion-based synthetic data generation, probabilistic federated Faster R-CNN, and inconsistent-category distillation, outperforming prior privacy-preserving baselines by 2.1%.
-
Investigation of cardinality classification for bacterial colony counting using explainable artificial intelligence
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.
-
Learning Class Difficulty in Imbalanced Histopathology Segmentation via Dynamic Focal Attention
Dynamic Focal Attention learns class-specific difficulty via per-class biases in attention logits, improving Dice and IoU on imbalanced histopathology segmentation benchmarks.
-
Hypergraph-State Collaborative Reasoning for Multi-Object Tracking
HyperSSM integrates hypergraphs and state space models to let correlated objects mutually refine motion estimates, stabilizing trajectories under noise and occlusion for state-of-the-art multi-object tracking.
-
Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization
ST-GD adapts Grounding DINO with about 10 million trainable parameters via adapters and a temporal decoder to achieve competitive performance on limited-data spatio-temporal video grounding benchmarks.
-
MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling
MapATM improves lane divider AP by 4.6 and mAP by 2.6 on NuScenes by treating actor trajectories as structural priors for road geometry.
-
EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
EviRCOD integrates reference-guided deformable encoding, uncertainty-aware evidential decoding, and boundary refinement to achieve state-of-the-art performance on referring camouflaged object detection benchmarks with calibrated uncertainty.
-
SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure Units
SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.
-
Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matching
GREATEN fuses surface normals with image features via gated contextual-geometric fusion and efficient sparse attentions to cut stereo matching errors by up to 30% on real datasets when trained solely on synthetic data.
-
Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer
The OG-ReG Transformer achieves state-of-the-art results on Kinetics-400, Something-Something v2, and Diving-48 by combining global glance and local gaze processing paths.
-
HQF-Net: A Hybrid Quantum-Classical Multi-Scale Fusion Network for Remote Sensing Image Segmentation
HQF-Net reports mIoU gains on three remote-sensing benchmarks by adding quantum circuits to skip connections and a mixture-of-experts bottleneck inside a classical U-Net fused with a DINOv3 backbone.
-
Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion
VoxSAMNet introduces sparsity-aware deformable attention via a dummy node and foreground modulation with dropout plus text-guided filtering to reach new state-of-the-art mIoU of 18.2% on SemanticKITTI and 20.2% on SSCBench-KITTI-360 for monocular 3D scene completion.
-
Multi-Modal Sensor Fusion using Hybrid Attention for Autonomous Driving
MMF-BEV fuses camera and radar branches with deformable self- and cross-attention, outperforming unimodal baselines on the VoD 4D radar dataset through a two-stage training process.
-
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
MDDCNet combines Mamba blocks with deformable dilated convolutions, enhanced feed-forward networks, and an attention-aggregating feature pyramid to achieve better multi-scale traffic object detection than prior detectors.
-
Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions
Intermediate-depth ResNet backbones in RT-DETR maintain near-perfect accuracy for round objects under lighting or background shifts, with ResNet50 best for illumination changes and ResNet34 best for background changes.