Search Results for author:
Found 10 papers, 5 papers with code
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation
To this end, we propose a dual student framework with trustworthy progressive learning (DuPL).
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
ClickVOS: Click Video Object Segmentation
To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame.
Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples.
When Mining Electric Locomotives Meet Reinforcement Learning
In this paper, we present how to apply RL to the autonomous control of mining electric locomotives.
Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) with image-level annotations has achieved great processes through class activation map (CAM).
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture
The occlusion problem heavily degrades the localization performance of face alignment.
Ranked #3 on
Face Alignment
on COFW-68
Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization
Moreover, the SRN augments the training data by synthesizing occluded faces.
Unsupervised Learning of Multi-level Structures for Anomaly Detection
This paper first introduces a novel method to generate anomalous data by breaking up global structures while preserving local structures of normal data at multiple levels.
Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks
We argue that exploring the weaknesses of the detector so as to remedy them is a promising method of robust facial landmark detection.
Ranked #5 on
Face Alignment
on COFW-68
Learning Segmentation Masks with the Independence Prior
We get appealing results in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image.
