Search Results for author:
Found 15 papers, 4 papers with code
Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?
For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives.
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
However, for unsupervised pretraining, the popular contrastive learning requires a large batch size and, therefore, a lot of resources.
Spatio-temporal predictive tasks for abnormal event detection in videos
Abnormal event detection in videos is a challenging problem, partly due to the multiplicity of abnormal patterns and the lack of their corresponding annotations.
Ranked #2 on
Anomaly Detection
on UCSD Ped2
Object-centric and memory-guided normality reconstruction for video anomaly detection
This paper addresses video anomaly detection problem for videosurveillance.
Ranked #3 on
Anomaly Detection
on UCSD Peds2
Describe me if you can! Characterized Instance-level Human Parsing
In addition, we propose HPTR, a new bottom-up multi-task method based on transformers as a fast and scalable baseline.
End-to-end Person Search Sequentially Trained on Aggregated Dataset
In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose.
Detecting Human-to-Human-or-Object (H2O) Interactions with DIABOLO
This can be an issue for HOI detection methods whose complexity depends on the number of people, targets or interactions.
A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification
(ii) General good practices for Pseudo-Labeling, directly deduced from the interpretation of the proposed theoretical framework, in order to improve the target re-ID performance.
Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
However, the effectiveness of these approaches heavily depends on the choice of some hyperparameters (HP) that affect the generation of pseudo-labels by clustering.
Optimal Transport as a Defense Against Adversarial Attacks
This leads to SAT (Sinkhorn Adversarial Training), a more robust defense against adversarial attacks.
PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting.
Ranked #1 on
on MVTecAD
Improving Few-Shot Learning through Multi-task Representation Learning Theory
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task.
Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of meta-learning theory into practice for the popular task of few-shot classification.
Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling
A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data).
Classifying All Interacting Pairs in a Single Shot
In this paper, we introduce a novel human interaction detection approach, based on CALIPSO (Classifying ALl Interacting Pairs in a Single shOt), a classifier of human-object interactions.
