Log In Sign Up

Unsupervised Deep Domain Adaptation for Pedestrian Detection

by   Lihang Liu, et al.

This paper addresses the problem of unsupervised domain adaptation on the task of pedestrian detection in crowded scenes. First, we utilize an iterative algorithm to iteratively select and auto-annotate positive pedestrian samples with high confidence as the training samples for the target domain. Meanwhile, we also reuse negative samples from the source domain to compensate for the imbalance between the amount of positive samples and negative samples. Second, based on the deep network we also design an unsupervised regularizer to mitigate influence from data noise. More specifically, we transform the last fully connected layer into two sub-layers - an element-wise multiply layer and a sum layer, and add the unsupervised regularizer to further improve the domain adaptation accuracy. In experiments for pedestrian detection, the proposed method boosts the recall value by nearly 30 the same. Furthermore, we perform our method on standard domain adaptation benchmarks on both supervised and unsupervised settings and also achieve state-of-the-art results.


Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where l...

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

Multimodal information (e.g., visible and thermal) can generate robust p...

Unsupervised Domain Adaptation via Calibrating Uncertainties

Unsupervised domain adaptation (UDA) aims at inferring class labels for ...

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Unsupervised domain adaptation (UDA) involves a supervised loss in a lab...

Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection

False positive is one of the most serious problems brought by agnostic d...

Domain Adaptation from Synthesis to Reality in Single-model Detector for Video Smoke Detection

This paper proposes a method for video smoke detection using synthetic s...

Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models

Recognition across domains has recently become an active topic in the re...