2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track

• URL: http://arxiv.org/abs/2110.13064v1
• Date: Mon, 25 Oct 2021 15:58:19 GMT
• Title: 2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track
• Authors: Manoj Acharya, Christopher Kanan
• Abstract summary: We adapt ResNet50-FPN as the baseline and try several improvements for the final submission model. We find that task-specific replay scheme, learning rate scheduling, model calibration, and using original image scale helps to improve performance for both large and small objects in images.
• Score: 35.06282647572304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge. We adapt ResNet50-FPN as the baseline and try several improvements for the final submission model. We find that task-specific replay scheme, learning rate scheduling, model calibration, and using original image scale helps to improve performance for both large and small objects in images. Our team `hypertune28' secured the second position among 52 participants in the challenge. This work will be presented at the ICCV 2021 Workshop on Self-supervised Learning for Next-Generation Industry-level Autonomous Driving (SSLAD).

Related papers

• Fine-Grained Hard Negative Mining: Generalizing Mitosis Detection with a Fifth of the MIDOG 2022 Dataset [1.2183405753834562]
  We describe a candidate deep learning solution for the Mitosis Domain Generalization Challenge 2022 (MIDOG) Our approach consists in training a rotation-invariant deep learning model using aggressive data augmentation. Our model ensemble achieved a F1-score of.697 on the final test set after automated evaluation.
  arXiv  Detail & Related papers  (2023-01-03T13:06:44Z)
• Highly Accurate Dichotomous Image Segmentation [139.79513044546]
  A new task called dichotomous image segmentation (DIS) aims to segment highly accurate objects from natural images. We collect the first large-scale dataset, DIS5K, which contains 5,470 high-resolution (e.g., 2K, 4K or larger) images. We also introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training.
  arXiv  Detail & Related papers  (2022-03-06T20:09:19Z)
• Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge [57.647371468876116]
  We introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively.
  arXiv  Detail & Related papers  (2021-07-27T06:36:06Z)
• NTIRE 2021 Multi-modal Aerial View Object Classification Challenge [88.89190054948325]
  We introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR. This challenge is composed of two different tracks using EO and SAR imagery. We discuss the top methods submitted for this competition and evaluate their results on our blind test set.
  arXiv  Detail & Related papers  (2021-07-02T16:55:08Z)
• Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track [78.64815984927425]
  The goal of weakly-supervised temporal action localization is to temporally locate and classify action of interest in untrimmed videos. We adopt the two-stream consensus network (TSCN) as the main framework in this challenge. Our solution ranked 2rd in this challenge, and we hope our method can serve as a baseline for future academic research.
  arXiv  Detail & Related papers  (2021-06-21T03:36:36Z)
• Relation Modeling in Spatio-Temporal Action Localization [25.09128518931016]
  This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation methods for relation-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.
  arXiv  Detail & Related papers  (2021-06-15T11:40:18Z)
• An Empirical Study of Vehicle Re-Identification on the AI City Challenge [19.13038665501964]
  The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. We mainly focus on four points, i.e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge. With aforementioned techniques, our method finally achieves 0.7445 mAP score, yielding the first place in the competition.
  arXiv  Detail & Related papers  (2021-05-20T12:20:52Z)
• LID 2020: The Learning from Imperfect Data Challenge Results [242.86700551532272]
  Learning from Imperfect Data workshop aims to inspire and facilitate the research in developing novel approaches. We organize three challenges to find the state-of-the-art approaches in weakly supervised learning setting. This technical report summarizes the highlights from the challenge.
  arXiv  Detail & Related papers  (2020-10-17T13:06:12Z)
• 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge [24.368684444351068]
  We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Our overall detection system achieves 36.6$%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.
  arXiv  Detail & Related papers  (2020-07-17T09:21:29Z)

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.