Related papers: Fusion Complexity Inversion: Why Simpler Cross Vie…

In this paper, we propose an efficient human pose estimation network -- SFM (slender fusion model) by fusing multi-level features and adding lightweight attention blocks -- HSA (High-Level Spatial Attention). Many existing methods on…

Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, without access to original training data. Unfortunately, its application to…

Multimodal image fusion (MMIF) integrates information from different modalities to obtain a comprehensive image, aiding downstream tasks. However, existing research focuses on complementary information fusion and training strategies,…

This paper proposes and evaluates, for the first time, a top-down (dorsal view), depth-only deep learning system for accurately identifying individual cattle and provides associated code, datasets, and training weights for immediate…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories. However, for multisource…

Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models' decisions has grown…

Edge devices increasingly run multimodal sensing pipelines that must remain accurate despite fluctuating power budgets and unpredictable sensor dropout. Existing pruning methods fail under these conditions: they generally require…

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…

Biomass estimation of oilseed rape is crucial for optimizing crop productivity and breeding strategies. While UAV-based imaging has advanced high-throughput phenotyping, current methods often rely on orthophoto images, which struggle with…

Herbicide field trials require accurate identification of plant species and assessment of herbicide-induced damage across diverse environments. While general-purpose vision foundation models have shown promising results in complex visual…

Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as…

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Multispectral imagery is frequently incorporated into agricultural tasks, providing valuable support for applications such as image segmentation, crop monitoring, field robotics, and yield estimation. From an image segmentation perspective,…

A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…

Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion system trained on 2,068,901 records from 404 monitoring locations in 29 African countries…

Detecting plant diseases is a crucial aspect of modern agriculture, as it plays a key role in maintaining crop health and increasing overall yield. Traditional approaches, though still valuable, often rely on manual inspection or…

Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention responses in Transformers, we empirically observe two…

Breast ultrasound imaging is an important noninvasive method for early breast cancer diagnosis, but automatic benign/malignant classification remains challenging due to tumor heterogeneity, blurred boundaries, and data imbalance. To improve…

Fine-grained visual categorization (FGVC) is a challenging task due to similar visual appearances between various species. Previous studies always implicitly assume that the training and test data have the same underlying distributions, and…