Vision Transformer-Based Multi-Level Feature Fusion for Multi-Label Sewer Defect Classification

• URL: http://arxiv.org/abs/2609.11375v1
• Date: Thu, 10 Sep 2026 11:11:03 GMT
• Title: Vision Transformer-Based Multi-Level Feature Fusion for Multi-Label Sewer Defect Classification
• Abstract summary: This study develops Sewer-Transformer-ML, a hierarchical vision Transformer with multi-level feature fusion.<n>On the Sewer-ML test set, Sewer-Transformer-ML achieved an $F2_textCIW$ of 65.68% and an $FtextNormal$ of 92.68%.
• Score: 17.141680489940352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated classification of sewer defects is essential for infrastructure condition assessment and maintenance decision-making, but existing deep learning methods struggle to balance classification accuracy and computational complexity in large-scale multi-label scenarios. This study develops Sewer-Transformer-ML, a hierarchical vision Transformer with multi-level feature fusion, together with two lightweight architectures, Sewer-MobileNet-ML and Sewer-Mobile-TransNet, for resource-constrained inspection scenarios. On the Sewer-ML test set, Sewer-Transformer-ML-Base achieved an $F2_{\text{CIW}}$ of 65.68% and an $F1_{\text{Normal}}$ of 92.68%, ranking first on the public leaderboard and exceeding the second-ranked method by 7.6 percentage points in $F2_{\text{CIW}}$. Sewer-MobileNet-ML achieved an $F2_{\text{CIW}}$ of 65.73% with only 17 M parameters, representing an approximately 95% parameter reduction relative to the base model. Under the standard Sewer-Capsule data split, Sewer-Mobile-TransNet achieved 96.43% classification accuracy. When the training set was reduced to 1,177 images, pretraining on Sewer-ML consistently improved model performance. Ablation experiments further showed that direct concatenation was more effective for Transformer features, whereas attention-based fusion better supported multiscale CNN features. These findings provide a computational basis for automated sewer inspection, lightweight model design, and adaptation across civil infrastructure inspection platforms.

Related papers

• DREAM Technical Report [53.37525197047151]
  We present DREAM, an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them.<n> DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%.<n>Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with
  arXiv  Detail & Related papers  (2026-08-10T10:35:32Z)
• YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition [78.52944812151664]
  Large language models (LLMs) drive significant financial innovations, yet their deployment is bottlenecked by KV cache memory overhead.<n>We propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline built on the Huawei Ascend ecosystem.
  arXiv  Detail & Related papers  (2026-06-04T08:44:37Z)
• Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment [4.976815699476327]
  We present Slimmable ConvNeXt, which shows that ConvNeXt's modern design, specifically LayerNorm and inverted bottlenecks, makes it particularly suited for channel-width slimming.<n>On ImageNet-1k, Slimmable ConvNeXt-T with 3works achieves 80.8% top-1 accuracy at 4.5 GMACs and 77.4% at 1.2 GMACs, trained from scratch for 600 epochs.
  arXiv  Detail & Related papers  (2026-05-21T16:20:18Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Mono2Sls: Automated Monolith-to-Serverless Migration via Multi-Stage Pipeline with Static Analysis [39.8879463570937]
  We present Mono2Sls, an automated pipeline that converts monolithic web backends into deployable AWS SAM applications.<n>Mono2Sls achieves 100% deployment success without manual fixes.<n>It also reaches 66.1% end-to-end correctness and 98.7% API-coverage F1.
  arXiv  Detail & Related papers  (2026-04-27T14:44:07Z)
• LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging [11.135582038431368]
  We introduce LARV, a training-free, data-free, merger-agnostic Layer-wise Adaptive Rescaling Veneer.<n>LARV adaptively suppresses shallow-layer interference and amplifies deeper-layer alignment using a simple deterministic schedule.<n> Layerwise analysis and corruption tests indicate that LARV suppresses shallow-layer interference while modestly amplifying deeper, task-stable features.
  arXiv  Detail & Related papers  (2026-02-10T05:10:31Z)
• Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling [90.87033586963828]
  Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs)<n>We propose Self-Consistency Sampling (SCS) to correct this issue.<n>Based on Qwen2.5-VL-7B-Instruct, SCS improves accuracy by up to 7.7 percentage points on six multimodal benchmarks with negligible extra computation.
  arXiv  Detail & Related papers  (2025-11-13T18:59:57Z)
• Transformer-based Federated Learning for Multi-Label Remote Sensing Image Classification [2.3255040478777755]
  We investigate the capability of state-of-the-art transformer architectures to address the challenges related to non-IID training data across various clients. The considered transformer architectures increase the ability with the cost of higher local training and aggregation complexities.
  arXiv  Detail & Related papers  (2024-05-24T10:13:49Z)
• Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder [56.673599764041384]
  We present a novel decoder-focused multi-task classification architecture Cross-Task Graph Neural Network (CT-GNN) CT-GNN refines the disjointed per-task predictions using cross-task information. We achieve state-of-the-art performance on all four classification tasks in the Sewer-ML dataset.
  arXiv  Detail & Related papers  (2021-11-15T15:36:50Z)
• Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark [29.728476976320913]
  We present a novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML. The dataset consists of 1.3 million images annotated by professional sewer inspectors from three different utility companies over nine years. We also present a benchmark algorithm and a novel metric for assessing performance.
  arXiv  Detail & Related papers  (2021-03-19T16:32:37Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)

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.