First Place Solution to the MLCAS 2025 GWFSS Challenge: The Devil is in the Detail and Minority

• URL: http://arxiv.org/abs/2508.17305v1
• Date: Sun, 24 Aug 2025 11:14:18 GMT
• Title: First Place Solution to the MLCAS 2025 GWFSS Challenge: The Devil is in the Detail and Minority
• Abstract summary: We present our solution for the MLCAS 2025 GWFSS Challenge.<n>The challenge hosts a semantic segmentation competition specific to wheat plants.<n>By probing visualizations, we identify the key -- the stem matters.
• Score: 6.292804208359623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present our solution during the participation of the MLCAS 2025 GWFSS Challenge. This challenge hosts a semantic segmentation competition specific to wheat plants, which requires to segment three wheat organs including the head, leaf, and stem, and another background class. In 2025, participating a segmentation competition is significantly different from that in previous years where many tricks can play important roles. Nowadays most segmentation tricks have been well integrated into existing codebases such that our naive ViT-Adapter baseline has already achieved sufficiently good performance. Hence, we believe the key to stand out among other competitors is to focus on the problem nature of wheat per se. By probing visualizations, we identify the key -- the stem matters. In contrast to heads and leaves, stems exhibit fine structure and occupy only few pixels, which suffers from fragile predictions and class imbalance. Building on our baseline, we present three technical improvements tailored to stems: i) incorporating a dynamic upsampler SAPA used to enhance detail delineation; ii) leveraging semi-supervised guided distillation with stem-aware sample selection to mine the treasure beneath unlabeled data; and iii) applying a test-time scaling strategy to zoom in and segment twice the image. Despite being simple, the three improvements bring us to the first place of the competition, outperforming the second place by clear margins. Code and models will be released at https://github.com/tiny-smart/gwfss25.

Related papers

• EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge [69.56534058291463]
  HD-EPIC evaluates whether a vision-language model can reason over realistic first-person kitchen videos.<n> benchmark contains 26K multiple-choice questions across seven macro-categories.<n>EgoAdapt introduces three inference-time components: (1) category-conditioned routing with per-category prompts, frame budgets, and sampling rates; (2) option scoring that evaluates all candidate answers with letter-token likelihoods and generation agreement instead of relying on direct generation; and (3) test-time consistency adaptation that aggregates predictions across option permutations and verification-style prompts for ambiguous cases.
  arXiv  Detail & Related papers  (2026-05-23T10:16:51Z)
• C3S3: Complementary Competition and Contrastive Selection for Semi-Supervised Medical Image Segmentation [2.3441453628908238]
  We introduce C3S3, a novel semi-supervised segmentation model that integrates complementary competition and contrastive selection.<n>This design significantly sharpens boundary delineation and enhances overall precision.<n>The proposed C3S3 undergoes rigorous validation on two publicly accessible datasets.
  arXiv  Detail & Related papers  (2025-06-09T02:34:19Z)
• SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation [12.168303995947795]
  We propose a novel Semantic-Guided Triplet Co-training framework.<n>It achieves high-end medical image segmentation by only annotating three slices of a few volumetric samples.<n>Our method outperforms most state-of-the-art semi-supervised counterparts under sparse annotation settings.
  arXiv  Detail & Related papers  (2024-12-20T03:31:33Z)
• Image Segmentation in Foundation Model Era: A Survey [95.60054312319939]
  Current research in image segmentation lacks a detailed analysis of distinct characteristics, challenges, and solutions.<n>This survey seeks to fill this gap by providing a thorough review of cutting-edge research centered around FM-driven image segmentation.<n>An exhaustive overview of over 300 segmentation approaches is provided to encapsulate the breadth of current research efforts.
  arXiv  Detail & Related papers  (2024-08-23T10:07:59Z)
• Agriculture-Vision Challenge 2024 -- The Runner-Up Solution for Agricultural Pattern Recognition via Class Balancing and Model Ensemble [20.631333392618327]
  The Agriculture-Vision Challenge at CVPR 2024 aims at leveraging semantic segmentation models to produce pixel level semantic segmentation labels. We propose a mosaic data augmentation with a rare class sampling strategy to enrich long-tail class samples. Our methodology achieved a mean Intersection over Union (mIoU) score of 0.547 on the test set, securing second place in this challenge.
  arXiv  Detail & Related papers  (2024-06-18T04:59:04Z)
• Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery [51.73680703579997]
  We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images. objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads. We introduce a scale-adaptive semantic label fusion strategy that enhances the segmentation of objects of varying sizes. We then introduce a novel cross-view instance label grouping strategy to mitigate the multi-view inconsistency problem in the 2D instance labels.
  arXiv  Detail & Related papers  (2024-03-18T14:15:39Z)
• Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization [64.36097398869774]
  Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding. The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data. We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
  arXiv  Detail & Related papers  (2024-01-13T04:16:40Z)
• 3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW [68.56017675820897]
  In this paper, we introduce 3rd place solution for PVUW2023 VSS track. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation.
  arXiv  Detail & Related papers  (2023-06-04T07:50:38Z)
• CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not [109.69076457732632]
  We leverage CLIP for zero-shot sketch based image retrieval (ZS-SBIR) We put forward novel designs on how best to achieve this synergy. We observe significant performance gains in the region of 26.9% over previous state-of-the-art.
  arXiv  Detail & Related papers  (2023-03-23T17:02:00Z)
• PA-Seg: Learning from Point Annotations for 3D Medical Image Segmentation using Contextual Regularization and Cross Knowledge Distillation [14.412073730567137]
  We propose to annotate a segmentation target with only seven points in 3D medical images, and design a two-stage weakly supervised learning framework PA-Seg. In the first stage, we employ geodesic distance transform to expand the seed points to provide more supervision signal. In the second stage, we use predictions obtained by the model pre-trained in the first stage as pseudo labels.
  arXiv  Detail & Related papers  (2022-08-11T07:00:33Z)
• Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation [74.67594286008317]
  This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. We propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level.
  arXiv  Detail & Related papers  (2022-06-05T05:28:32Z)
• A Few Guidelines for Incremental Few-Shot Segmentation [57.34237650765928]
  Given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones. We show how the main problems of end-to-end training in this scenario are. i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and. ii) the forgetting of old classes, that we can fix with regularization strategies.
  arXiv  Detail & Related papers  (2020-11-30T20:45:56Z)

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.