Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond

• URL: http://arxiv.org/abs/2201.03176v1
• Date: Mon, 10 Jan 2022 06:00:26 GMT
• Title: Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond
• Authors: Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, and Ling Shao
• Abstract summary: We show that, current pedestrian detectors poorly handle even small domain shifts in cross-dataset evaluation. We attribute the limited generalization to two main factors, the method and the current sources of data. We propose a progressive fine-tuning strategy which improves generalization.
• Score: 82.37430109152383
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pedestrian detection is the cornerstone of many vision based applications, starting from object tracking to video surveillance and more recently, autonomous driving. With the rapid development of deep learning in object detection, pedestrian detection has achieved very good performance in traditional single-dataset training and evaluation setting. However, in this study on generalizable pedestrian detectors, we show that, current pedestrian detectors poorly handle even small domain shifts in cross-dataset evaluation. We attribute the limited generalization to two main factors, the method and the current sources of data. Regarding the method, we illustrate that biasness present in the design choices (e.g anchor settings) of current pedestrian detectors are the main contributing factor to the limited generalization. Most modern pedestrian detectors are tailored towards target dataset, where they do achieve high performance in traditional single training and testing pipeline, but suffer a degrade in performance when evaluated through cross-dataset evaluation. Consequently, a general object detector performs better in cross-dataset evaluation compared with state of the art pedestrian detectors, due to its generic design. As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians. Therefore, benchmarks curated by crawling the web (which contain diverse and dense scenarios), are an efficient source of pre-training for providing a more robust representation. Accordingly, we propose a progressive fine-tuning strategy which improves generalization. Code and models cab accessed at https://github.com/hasanirtiza/Pedestron.

Related papers

• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Unsupervised Adaptation from Repeated Traversals for Autonomous Driving [54.59577283226982]
  Self-driving cars must generalize to the end-user's environment to operate reliably. One potential solution is to leverage unlabeled data collected from the end-users' environments. There is no reliable signal in the target domain to supervise the adaptation process. We show that this simple additional assumption is sufficient to obtain a potent signal that allows us to perform iterative self-training of 3D object detectors on the target domain.
  arXiv  Detail & Related papers  (2023-03-27T15:07:55Z)
• CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving [117.87070488537334]
  We introduce a challenging dataset named CODA that exposes this critical problem of vision-based detectors. The performance of standard object detectors trained on large-scale autonomous driving datasets significantly drops to no more than 12.8% in mAR. We experiment with the state-of-the-art open-world object detector and find that it also fails to reliably identify the novel objects in CODA.
  arXiv  Detail & Related papers  (2022-03-15T08:32:56Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• Generalizable Pedestrian Detection: The Elephant In The Room [82.37430109152383]
  We find that existing state-of-the-art pedestrian detectors, though perform quite well when trained and tested on the same dataset, generalize poorly in cross dataset evaluation. We illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection.
  arXiv  Detail & Related papers  (2020-03-19T14:14:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.