When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe

• URL: http://arxiv.org/abs/2607.23024v1
• Date: Sat, 25 Jul 2026 03:51:49 GMT
• Title: When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe
• Abstract summary: This study compares five architectures VGG16, MobileNetV2, InceptionV3, AlexNet, and CNN on the DeepGlobe Land Cover Classification dataset.<n>At 24.98 MB, MobileNetV2_v1 had the highest overall accuracy (0.7906) and mean Intersection over Union (0.4625)<n>These results show that lightweight, transfer-learned models can match or outperform deeper models in resource-constrained remote-sensing environments.
• Score: 0.3093890460224435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution satellite imagery is the backbone of good land-cover classification, and without that, environmental monitoring, urban planning, and sustainable resource management all fall short. Deep learning architectures perform well in semantic segmentation, but the efficiency-accuracy trade-off across classical convolutional encoders is not well quantified under controlled, reproducible conditions. This study compares five architectures VGG16, MobileNetV2, InceptionV3, AlexNet, and CNN on the DeepGlobe Land Cover Classification dataset using three progressively optimized iterations to isolate regularisation, transfer learning, and architectural depth. To ensure performance differentials reflect architectural properties, all experiments used identical preprocessing, hyperparameter, and training protocols without data augmentation or class-imbalance correction. At 24.98 MB, MobileNetV2_v1 had the highest overall accuracy (0.7906) and mean Intersection over Union (0.4625), outperforming deeper alternatives like InceptionV3_v2 (125.17 MB, accuracy 0.7610) and VGG16_v2 (71.13 MB, accuracy 0.7653). Class-wise analysis showed strength in urban, agricultural, and water categories, but rangeland-barren confusion showed that architectural optimization alone cannot optimize spectrally similar minority classes. Strong spatial generalization and crisp boundary delineation were confirmed on held-out test imagery, validating operational applicability. These results show that lightweight, transfer-learned models can match or outperform deeper models in resource-constrained remote-sensing environments, enabling scalable land-cover mapping.

Related papers

• Rethinking Attention Locality in Spiking Transformers [50.00501275379363]
  Spiking Transformers provide a promising paradigm for efficient visual processing with spike-driven computation.<n>Their Softmax-free Spiking Self-Attention (SSA) struggles to establish spatially localized token interactions.<n>We propose Spatially Contiguous Local Attention with Boundary Continuity Pathway (SCLA-BCP)<n>Our approach improves mAP@50 by up to 9.50% on COCO on 2017 and mIoU by up to 3.42% on ADE20K.
  arXiv  Detail & Related papers  (2026-08-09T07:36:17Z)
• Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Architectures [48.83701310501069]
  We investigate the impact of schedulers on classification accuracy across a diverse pool of architectures.<n>We applied 25 scheduler configurations across nine PyTorch families, evaluating a total of 3,938 model variants on CIFAR-10.<n>The results show that the choice of scheduler depends heavily on the architecture: CosineAnnealingWarmRestarts and CyclicLR consistently outperform basic decay strategies.
  arXiv  Detail & Related papers  (2026-07-09T14:06:39Z)
• ArcGate: Adaptive Arctangent Gated Activation [62.5098969984518]
  This paper proposes the Adaptive Arctangent Gated Activation function, a flexible formulation that generates a broad spectrum of activation shapes.<n>We evaluate ArcGate on three widely used remote sensing benchmarks: PatternNet, UC Merced Land Use, and the 13-band EuroSAT MSI multispectral dataset.
  arXiv  Detail & Related papers  (2026-05-14T08:00:46Z)
• Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation [0.0]
  We present GraphDepth, a monocular depth estimation architecture that integrates Graph Neural Networks (GNNs) within a convolutional encoder-decoder framework.<n>Our approach embeds efficient GraphSAGE layers at multiple scales of a ResNet-101 U-Net backbone.<n> Experiments on NYU Depth V2, WHU Aerial, ETH3D, and Mid-Air benchmarks demonstrate competitive accuracy within 4.6% of state-of-the-art transformers.
  arXiv  Detail & Related papers  (2026-05-11T09:21:04Z)
• Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs [2.111646739533638]
  Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility.<n>We propose a lightweight 'Online Architecture' strategy by strategically inserting Global Average Pooling layers at various network depths.<n>This strategy achieves a massive 98% reduction in trainable parameters (from 5.2M to just 82K) and a 90% reduction in total network size.
  arXiv  Detail & Related papers  (2026-04-30T13:52:42Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• Comparative Evaluation of CNN Architectures for Neural Style Transfer in Indonesian Batik Motif Generation: A Comprehensive Study [0.5161531917413708]
  This study presents a systematic comparative analysis of five widely used CNN backbones, VGG16, VGG19, Inception V3, ResNet50, and ResNet101.<n>Results show that backbone selection does not yield statistically significant differences in structural similarity.<n>ResNet-based architectures achieve approximately 5-6x faster convergence than VGG models.
  arXiv  Detail & Related papers  (2025-12-31T11:06:09Z)
• Towards Accurate and Efficient Waste Image Classification: A Hybrid Deep Learning and Machine Learning Approach [0.05599792629509228]
  This study provides a comprehensive comparison of three paradigms: (1) machine learning algorithms using handcrafted features, (2) deep learning architectures, including ResNet variants and EfficientNetV2S, and (3) a hybrid approach that utilizes deep models for feature extraction combined with classical classifiers such as Support Vector Machine and Logistic Regression to identify the most effective strategy.<n>Experiments on three public datasets - TrashNet, Garbage Classification, and a refined Household Garbage dataset- demonstrate that the hybrid method consistently outperforms the others, achieving up to 100% accuracy on TrashNet and the refined Household set, and 99.87% on Garbage Classification, thereby surpassing state-of-the
  arXiv  Detail & Related papers  (2025-10-22T08:32:51Z)
• Classification of Geographical Land Structure Using Convolution Neural Network and Transfer Learning [1.024113475677323]
  This study can produce a set of applications such as urban planning and development, environmental monitoring, disaster management, etc. This article developed a deep learning-based approach to automate the process of classifying geographical land structures.
  arXiv  Detail & Related papers  (2024-11-19T11:01:30Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)
• SmoothNets: Optimizing CNN architecture design for differentially private deep learning [69.10072367807095]
  DPSGD requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private training. We distilled a new model architecture termed SmoothNet, which is characterised by increased robustness to the challenges of DP-SGD training.
  arXiv  Detail & Related papers  (2022-05-09T07:51:54Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)

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.