Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding

• URL: http://arxiv.org/abs/2606.23113v1
• Date: Mon, 22 Jun 2026 09:57:55 GMT
• Title: Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding
• Abstract summary: The ICRA 2026 GOOSE 2D Fine-Grained Semantic Challenge requires parsing unstructured outdoor scenes from four camera platforms into 56 fine-grained categories.<n>Our approach pairs foundation vision encoders with a Mask2Former decoder, and trains them with a strong recipe.<n>Our submission achieves 75.40% composite mIoU and wins the second place of the challenge.
• Score: 43.9978897868123
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor scenes from four camera platforms into 56 fine-grained categories. Our approach pairs foundation vision encoders (including DINOv3, SigLIP2, and InternImage) with a Mask2Former decoder, and trains them with a strong recipe including long training schedules, exponential moving average, a larger crop size, and multi-scale plus flip test-time augmentation. The three encoders, chosen for their complementary pretraining objectives, are combined into a pretraining-diverse ensemble through per-class validation-IoU weighting. Evaluated on the official GOOSE test set, our submission achieves 75.40% composite mIoU and wins the second place of the challenge. Our study further shows that the encoder's pretraining recipe, rather than its parameter count or the decoder design, is the dominant factor for accuracy on this benchmark.

Related papers

• Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Exploring Query-Based Segmentation and Increased Spatial Context for Outdoor Scene Understanding [2.685567215235468]
  We present our submission to the GOOSE 2D Fine-Grained Semantic Challenge, organized as part of the Workshop on Field Robotics at ICRA 2026.<n>The challenge combines data from the GOOSE and GOOSE-Ex datasets, annotated using a hierarchical taxonomy of 56 fine-grained classes and 11 broader categories.<n>Our final submission achieves an mIoU of 69.6% on the challenge test set, providing a strong baseline for fine-grained semantic segmentation in outdoor environments.
  arXiv  Detail & Related papers  (2026-06-19T14:13:04Z)
• SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation [3.487520041555239]
  We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Challenge.<n>Our model adapts the image of a recent visual foundation model, Segment Anything Model 3.
  arXiv  Detail & Related papers  (2026-06-18T11:54:07Z)
• Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Leveraging DINOv3 for Robust Outdoor Scene Understanding in Field Robotics [8.77371742508379]
  The GOOSE 2D Fine-Grained Semantic Challenge evaluates dense semantic segmentation of off-road imagery.<n>We present the first-place solution to this challenge.
  arXiv  Detail & Related papers  (2026-06-17T01:13:22Z)
• Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs [50.3757247538081]
  We retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline.<n>We decompose each encoder's contribution into two axes, Capacity and Necessity.<n>Per-encoder pre-projector effective rank explains the residual score variation.
  arXiv  Detail & Related papers  (2026-06-02T16:46:42Z)
• TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge [71.10535279591527]
  We present our solution, termed TempRet, to the CVPR 2026 EPIC-KITCHENS-100 MIR challenge.<n>Our approach builds upon a CLIP-based dual-encoder backbone and introduces two key components to address the temporal and cross-modal challenges.<n>Our method achieves 67.97% average mAP and 82.92% average nDCG on the EK-100 MIR benchmark.
  arXiv  Detail & Related papers  (2026-05-23T08:37:39Z)
• End-to-End Training for Unified Tokenization and Latent Denoising [82.91537591286554]
  We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion.<n>UNITE consists of a Generative that serves as both image tokenizer and latent generator via weight sharing.<n>We show that single stage joint training of tokenization & generation from scratch is feasible.
  arXiv  Detail & Related papers  (2026-03-23T17:59:49Z)
• LEADER: Lightweight End-to-End Attention-Gated Dual Autoencoder for Robust Minutiae Extraction [0.05978532290288763]
  This paper introduces LEADER (Lightweight End-to-end Attention-gated Dual autoencodER), a neural network that maps raw fingerprint images to minutiae descriptors.<n>It employs a novel "Castle-Moat-Rampart" ground-truth encoding and a dual-autoencoder structure, interconnected through an attention-gating mechanism.<n>It attains a 34% higher F1-score on the NIST SD27 dataset compared to specialized latent minutiae extractors.
  arXiv  Detail & Related papers  (2026-02-17T11:02:28Z)
• Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors [117.61449210940955]
  We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. We introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. We generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames.
  arXiv  Detail & Related papers  (2023-06-21T06:18:05Z)
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [149.78470371525754]
  We treat semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR) SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes.
  arXiv  Detail & Related papers  (2020-12-31T18:55:57Z)

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.