Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem. In this paper, we propose a simple but efficient and effective network, named DENet, which is composed of two components, i.e. , a detection network (DNet) and an encoder-decoder estimation network (ENet). We first run the DNet on the input image to detect and count individuals who can be segmented clearly. Then, the ENet is utilized to estimate the density maps of the remaining areas, typically with low resolution and high densities where individuals cannot be detected. For this purpose, we propose a modified Xception network as the encoder for feature extraction and a combination of dilated convolution and transposed convolution as the decoder. When evaluated on the ShanghaiTech Part A, UCF and WorldExpo’10 datasets, our DENet has achieved lower Mean Absolute Error (MAE) than those of the state-of-the-art methods.

Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions. However, there is still room for enhancement, particularly when considering constraints on computational resources. In this paper, we introduce HAFormer, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges. Specifically, we design a Hierarchy-Aware Pixel-Excitation (HAPE) module for adaptive multi-scale local feature extraction. During the global perception modeling, we devise an Efficient Transformer (ET) module streamlining the quadratic calculations associated with traditional Transformers. Moreover, a correlation-weighted Fusion (cwF) module selectively merges diverse feature representations, significantly enhancing predictive accuracy. HAFormer achieves high performance with minimal computational overhead and compact model size, achieving 74.2% mIoU on Cityscapes and 71.1% mIoU on CamVid test datasets, with frame rates of 105FPS and 118FPS on a single 2080Ti GPU. The source codes are available at https://github.com/XU-GITHUB-curry/HAFormer .

Identifying tiny objects from extremely low resolution (LR) UAV-based remote sensing images is generally considered as a very challenging task, because of very limited information in the object areas. In recent years, there have been very limited attempts to approach this problem. These attempts intend to deal with LR image classification by enhancing either the poor image quality or image representations.In this paper, we argue that the performance improvement in LR image classification is affected by the inconsistency of the information loss and learning priority on Low-Frequency (LF) components and High-Frequency (HF) components.To address this LF-HF inconsistency problem, we propose a Dual-Stream Representation Learning Generative Adversarial Network (DRL-GAN).The core idea is to produce super image representations optimal for LR recognition by simultaneously recovering the missing information in LF and HF components, respectively, under the guidance of high-resolution (HR) images.We evaluate the performance of DRL-GAN on the challenging task of LR image classification.A comparison of the experimental results on the LR benchmark, namely HRSC and CIFAR-10, and our newly collected “WIDER-SHIP” dataset demonstrates the effectiveness of our DRL-GAN, which significantly improves the classification performance, with up to 10% gain on average.

Detecting objects from images captured by Unmanned Aerial Vehicles (UAVs) is a highly demanding task. It is also considered a very challenging task due to the typically cluttered background and diverse dimensions of the foreground targets, especially small object areas that contain only very limited information. Multi-scale representation learning presents a remarkable approach to recognizing small objects. However, this strategy ignores the combination of the sub-parts in an object and also suffers from the background interference in the feature fusion process. To this end, we propose a Fine-grained Target Focusing Network (FiFoNet) which can effectively select a combination of multi-scale features for an object and block background interference, which further revitalizes the differentiability of the multi-scale feature representation. Furthermore, we propose a Global–Local Context Collector (GLCC) to extract global and local contextual information and enhance low-quality representations of small objects. We evaluate the performance of the proposed FiFoNet on the challenging task of object detection in UAV images. A comparison of the experiment results on three datasets, namely VisDrone2019, UAVDT, and our VisDrone_Foggy, demonstrates the effectiveness of FiFoNet, which outperforms the ten baseline and state-of-the-art models with remarkable performance improvements. When deployed on an edge device NVIDIA JETSON XAVIER NX, our FiFoNet only takes about 80 milliseconds to process an drone-captured image.

Bottom-up text detection methods play an important role in arbitrary-shape scene text detection but there are two restrictions preventing them from achieving their great potential, i.e., 1) the accumulation of false text segment detections, which affects subsequent processing, and 2) the difficulty of building reliable connections between text segments. Targeting these two problems, we propose a novel approach, named ``MorphText", to capture the regularity of texts by embedding deep morphology for arbitrary-shape text detection. Towards this end, two deep morphological modules are designed to regularize text segments and determine the linkage between them. First, a Deep Morphological Opening (DMOP) module is constructed to remove false text segment detections generated in the feature extraction process. Then, a Deep Morphological Closing (DMCL) module is proposed to allow text instances of various shapes to stretch their morphology along their most significant orientation while deriving their connections.Extensive experiments conducted on four challenging benchmark datasets (CTW1500, Total-Text, MSRA-TD500 and ICDAR2017) demonstrate that our proposed MorphText outperforms both top-down and bottom-up state-of-the-art arbitrary-shape scene text detection approaches.