Search Results for author:
Found 33 papers, 13 papers with code
Outlier detection by ensembling uncertainty with negative objectness
We therefore reconsider direct prediction of K+1 logits that correspond to K groundtruth classes and one outlier class.
Quantile-based Maximum Likelihood Training for Outlier Detection
Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning.
Real time dense anomaly detection by learning on synthetic negative data
Most approaches to dense anomaly detection rely on generative modeling or on discriminative methods that train with negative data.
Identifying Label Errors in Object Detection Datasets by Loss Inspection
In this work, we for the first time introduce a benchmark for label error detection methods on object detection datasets as well as a label error detection method and a number of baselines.
Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection
However, this strategy does not guarantee that the synthesized outlier features will have a low likelihood according to the other class-conditional Gaussians.
Hybrid Open-set Segmentation with Synthetic Negative Data
We evaluate our contributions on benchmarks for dense anomaly detection and open-set segmentation.
On Advantages of Mask-level Recognition for Outlier-aware Segmentation
Most dense recognition approaches bring a separate decision in each particular pixel.
Weakly supervised training of universal visual concepts for multi-domain semantic segmentation
For instance, pickups are labeled as trucks in VIPER, cars in Vistas, and vans in ADE20k.
Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification
We also validate our approach by comparing it with the related work on two road-scene classification datasets from the literature: Honda Scenes and FM3m.
Automatic universal taxonomies for multi-domain semantic segmentation
Training semantic segmentation models on multiple datasets has sparked a lot of recent interest in the computer vision community.
DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition
We blend these two predictions into a hybrid anomaly score which allows dense open-set recognition on large natural images.
Ranked #3 on
Scene Segmentation
on StreetHazards
(using extra training data)
Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation
Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or remote sensing.
Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data
Standard machine learning is unable to accommodate inputs which do not belong to the training distribution.
Ranked #2 on
Anomaly Detection
on Fishyscapes L&F
(using extra training data)
Multi-domain semantic segmentation with overlapping labels
Deep supervised models have an unprecedented capacity to absorb large quantities of training data.
Revisiting consistency for semi-supervised semantic segmentation
Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations.
Densely connected normalizing flows
Normalizing flows are bijective mappings between inputs and latent representations with a fully factorized distribution.
Ranked #2 on
Image Generation
on ImageNet 32x32
(bpd metric)
Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery.
Dense outlier detection and open-set recognition based on training with noisy negative images
Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution.
Dense open-set recognition with synthetic outliers generated by Real NVP
We obtain the synthetic outliers by sampling an RNVP model which is jointly trained to generate datapoints at the border of the training distribution.
Multimodal semantic forecasting based on conditional generation of future features
Most existing approaches address this problem as deterministic regression of future features or future predictions given observed frames.
Multi-domain semantic segmentation with pyramidal fusion
We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020.
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications.
Ranked #14 on
Anomaly Detection
on Fishyscapes L&F
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting.
Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings
We investigate tracking-by-detection approaches based on a deep learning detector, joint integrated probabilistic data association (JIPDA), and appearance-based tracking of deep correspondence embeddings.
Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images
Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks.
In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields.
Ranked #9 on
Semantic Segmentation
on ZJU-RGB-P
Discriminative out-of-distribution detection for semantic segmentation
Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes.
Robust Semantic Segmentation with Ladder-DenseNet Models
We present semantic segmentation experiments with a model capable to perform predictions on four benchmark datasets: Cityscapes, ScanNet, WildDash and KITTI.
Multiclass Road Sign Detection using Multiplicative Kernel
We consider the problem of multiclass road sign detection using a classification function with multiplicative kernel comprised from two kernels.
A Novel Georeferenced Dataset for Stereo Visual Odometry
In this work, we present a novel dataset for assessing the accuracy of stereo visual odometry.
Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data
This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition.
Classifying Traffic Scenes Using The GIST Image Descriptor
This paper investigates classification of traffic scenes in a very low bandwidth scenario, where an image should be coded by a small number of features.
Second Croatian Computer Vision Workshop (CCVW 2013)
Proceedings of the Second Croatian Computer Vision Workshop (CCVW 2013, http://www. fer. unizg. hr/crv/ccvw2013) held September 19, 2013, in Zagreb, Croatia.
