5th Place Solution for VSPW 2021 Challenge

• URL: http://arxiv.org/abs/2112.06379v1
• Date: Mon, 13 Dec 2021 02:27:05 GMT
• Title: 5th Place Solution for VSPW 2021 Challenge
• Authors: Jiafan Zhuang, Yixin Zhang, Xinyu Hu, Junjie Li, Zilei Wang
• Abstract summary: In this article, we introduce the solution we used in the VSPW 2021 Challenge. Our experiments are based on two baseline models, Swin Transformer and MaskFormer. Without using any external segmentation dataset, our solution ranked the 5th place in the private leaderboard.
• Score: 29.246666942808673
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this article, we introduce the solution we used in the VSPW 2021 Challenge. Our experiments are based on two baseline models, Swin Transformer and MaskFormer. To further boost performance, we adopt stochastic weight averaging technique and design hierarchical ensemble strategy. Without using any external semantic segmentation dataset, our solution ranked the 5th place in the private leaderboard. Besides, we have some interesting attempts to tackle long-tail recognition and overfitting issues, which achieves improvement on val subset. Maybe due to distribution difference, these attempts don't work on test subset. We will also introduce these attempts and hope to inspire other researchers.

Related papers

• The Fourth Monocular Depth Estimation Challenge [100.38910331027051]
  This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC) It focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. The challenge received a total of 24 submissions that outperformed the baselines on the test set. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.
  arXiv  Detail & Related papers  (2025-04-24T17:59:52Z)
• Constrained C-Test Generation via Mixed-Integer Programming [55.28927994487036]
  This work proposes a novel method to generate C-Tests; a form of cloze tests (a gap filling exercise) where only the last part of a word is turned into a gap. In contrast to previous works that only consider varying the gap size or gap placement to achieve locally optimal solutions, we propose a mixed-integer programming (MIP) approach. We publish our code, model, and collected data consisting of 32 English C-Tests with 20 gaps each (totaling 3,200 individual gap responses) under an open source license.
  arXiv  Detail & Related papers  (2024-04-12T21:35:21Z)
• PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks [9.31054333943453]
  We evaluate neural models for semantic parsing and meaning-to-text generation on the Parallel Meaning Bank. First, instead of the prior random split, we propose a more systematic splitting approach to improve the reliability of the standard test data. Second, except for the standard test set, we also propose two challenge sets: one with longer texts including discourse structure, and one that addresses compositional generalization.
  arXiv  Detail & Related papers  (2024-04-12T09:48:58Z)
• Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning [50.809769498312434]
  We propose a novel dataset pruning method termed as Temporal Dual-Depth Scoring (TDDS) Our method achieves 54.51% accuracy with only 10% training data, surpassing random selection by 7.83% and other comparison methods by at least 12.69%.
  arXiv  Detail & Related papers  (2023-11-22T03:45:30Z)
• Extending the Forward Forward Algorithm [1.448946342885513]
  We replicate Geoffrey Hinton's experiments on the MNIST dataset. We establish a baseline performance for the Forward Forward network on the IMDb movie reviews dataset. As far as we know, our results on this sentiment analysis task marks the first instance of the algorithm's extension beyond computer vision.
  arXiv  Detail & Related papers  (2023-07-09T15:26:18Z)
• 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)
• Rotation Invariance and Extensive Data Augmentation: a strategy for the Mitosis Domain Generalization (MIDOG) Challenge [1.52292571922932]
  We present the strategy we applied to participate in the MIDOG 2021 competition. The purpose of the competition was to evaluate the generalization of solutions to images acquired with unseen target scanners. We propose a solution based on a combination of state-of-the-art deep learning methods.
  arXiv  Detail & Related papers  (2021-09-02T10:09:02Z)
• 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection [3.600275712225597]
  We present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD) The MFD task has three key challenges including a large scale span, large variation of the ratio between height and width, and rich character set and mathematical expressions. Considering these challenges, we used Generalized Focal Loss (GFL), an anchor-free method, instead of the anchor-based method.
  arXiv  Detail & Related papers  (2021-07-12T16:03:16Z)
• 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)
• Coping with Label Shift via Distributionally Robust Optimisation [72.80971421083937]
  We propose a model that minimises an objective based on distributionally robust optimisation (DRO) We then design and analyse a gradient descent-proximal mirror ascent algorithm tailored for large-scale problems to optimise the proposed objective.
  arXiv  Detail & Related papers  (2020-10-23T08:33:04Z)
• Doubly-stochastic mining for heterogeneous retrieval [74.43785301907276]
  Modern retrieval problems are characterised by training sets with potentially billions of labels. With a large number of labels, standard losses are difficult to optimise even on a single example. We propose doubly-stochastic mining (S2M) to address both challenges.
  arXiv  Detail & Related papers  (2020-04-23T00:43:13Z)

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.