Search Results for author:
Found 13 papers, 10 papers with code
CARLA Drone: Monocular 3D Object Detection from a Different Perspective
Simulating drone views, it substantially expands the diversity of camera perspectives in existing benchmarks.
DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting
Although one approach against spurious surfaces has been widely used in the literature, we theoretically and experimentally show that it is equivalent to regularizing the surface area, resulting in over-smoothing.
Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals
Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global categories within an image corpus without any form of annotation.
Ranked #1 on
Unsupervised Semantic Segmentation
on Potsdam-3
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball
Hierarchy is a natural representation of semantic taxonomies, including the ones routinely used in image segmentation.
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball
Hierarchy is a natural representation of semantic taxonomies including the ones routinely used in image segmentation.
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
The models pretrained with MEM are also label-efficient and generalize well to the dense task of semantic image segmentation.
Ranked #1 on
Classification
on N-CARS
(using extra training data)
Semantic Self-adaptation: Enhancing Generalization with a Single Sample
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation.
Domain Generalization
One-shot Unsupervised Domain Adaptation
+2
Dense Unsupervised Learning for Video Segmentation
On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
Adaptive Generalization for Semantic Segmentation
In this work, we empirically study an adaptive inference strategy for semantic segmentation that adjusts the model to the test sample before producing the final prediction.
Self-supervised Augmentation Consistency for Adapting Semantic Segmentation
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate.
Ranked #17 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Single-Stage Semantic Segmentation from Image Labels
This is in contrast to earlier work that used only a single stage $-$ training one segmentation network on image labels $-$ which was abandoned due to inferior segmentation accuracy.
Markov Decision Process for Video Generation
We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping.
Actor-Critic Instance Segmentation
Most approaches to visual scene analysis have emphasised parallel processing of the image elements.
