Self-supervised monocular depth estimation improves in low-texture regions by using distance transforms on jointly estimated pre-semantic contours to create more informative loss signals.
hub
Deep residual learning for image recognition
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
representative citing papers
PicoEyes delivers a unified end-to-end model for full 3D gaze estimation including eye parameters, axes, segmentation and depth from monocular or binocular near-eye images, supported by a new large-scale multi-view dataset.
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
A unified multimodal learning framework models modality degradation as a continuous variable and uses a noise-aware quality estimator to adaptively weight fused representations under both intra- and inter-modality missingness.
SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.
AOI-SSL combines small-domain self-supervised pre-training of vision transformers with in-context patch retrieval to reduce labeled data needs and enable fast adaptation for semiconductor wire-bond segmentation.
TopoHR introduces hierarchical point/instance/semantic queries and a unified P2I+I2I topology module that reports SOTA gains on OpenLane-V2 subsets.
DAMP performs one-shot class unlearning by depth-aware projection removal of forget-specific directions, producing forgetting behavior closer to retraining from scratch than prior methods on image classification tasks.
CylinderDepth uses cylindrical spatial attention with non-learned weights to enforce cross-view consistency in self-supervised surround depth estimation.
PAL is a portable active learning method for object detection that uses class-specific logistic classifiers for uncertainty and image-level diversity to select annotation batches, showing better label efficiency than baselines on COCO, VOC, and BDD100K.
UGEL employs deep beta regression to estimate uncertainty in one forward pass, enabling faster convergence in edge learning for remote sensing image regression than active or semi-supervised baselines.
Supervised ClassMix and a Sup-Unsup Feature Discriminator yield an average 2.07% mIoU gain over standard semi-supervised methods on Chase and COVID-19 datasets.
FedDAP improves federated learning under domain shift by creating domain-specific global prototypes via similarity-weighted fusion and using them for domain-aware local feature alignment.
citing papers explorer
-
Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks
Self-supervised monocular depth estimation improves in low-texture regions by using distance transforms on jointly estimated pre-semantic contours to create more informative loss signals.
-
PicoEyes: Unified Gaze Estimation Framework for Mixed Reality with a Large-Scale Multi-View Dataset
PicoEyes delivers a unified end-to-end model for full 3D gaze estimation including eye parameters, axes, segmentation and depth from monocular or binocular near-eye images, supported by a new large-scale multi-view dataset.
-
Neural Collapse in Test-Time Adaptation
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
-
General Incomplete Multimodal Learning via Dynamic Quality Perception
A unified multimodal learning framework models modality degradation as a continuous variable and uses a noise-aware quality estimator to adaptively weight fused representations under both intra- and inter-modality missingness.
-
SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.
-
AOI-SSL: Self-Supervised Framework for Efficient Segmentation of Wire-bonded Semiconductors In Optical Inspection
AOI-SSL combines small-domain self-supervised pre-training of vision transformers with in-context patch retrieval to reduce labeled data needs and enable fast adaptation for semiconductor wire-bond segmentation.
-
TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations
TopoHR introduces hierarchical point/instance/semantic queries and a unified P2I+I2I topology module that reports SOTA gains on OpenLane-V2 subsets.
-
Class Unlearning via Depth-Aware Removal of Forget-Specific Directions
DAMP performs one-shot class unlearning by depth-aware projection removal of forget-specific directions, producing forgetting behavior closer to retraining from scratch than prior methods on image classification tasks.
-
CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation
CylinderDepth uses cylindrical spatial attention with non-learned weights to enforce cross-view consistency in self-supervised surround depth estimation.
-
Portable Active Learning for Object Detection
PAL is a portable active learning method for object detection that uses class-specific logistic classifiers for uncertainty and image-level diversity to select annotation batches, showing better label efficiency than baselines on COCO, VOC, and BDD100K.
-
Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing
UGEL employs deep beta regression to estimate uncertainty in one forward pass, enabling faster convergence in edge learning for remote sensing image regression than active or semi-supervised baselines.
-
Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
Supervised ClassMix and a Sup-Unsup Feature Discriminator yield an average 2.07% mIoU gain over standard semi-supervised methods on Chase and COVID-19 datasets.
-
FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift
FedDAP improves federated learning under domain shift by creating domain-specific global prototypes via similarity-weighted fusion and using them for domain-aware local feature alignment.