LLLiang Liu

Liang Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Liang Liu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

    by Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Chunhua Shen, Zhiguo Cao


  • Counting Crowd by Weighing Counts: A Sequential Decision-Making Perspective

    by Hao Lu, Liang Liu, Hu Wang, Zhiguo Cao

    We show that crowd counting can be formulated as a sequential decision-making (SDM) problem. Inspired by human counting, we evade one-step estimation mostly executed in existing counting models and decompose counting into sequential sub-decision problems. During implementation, a key insight is to interpret sequential counting as a physical process in reality—scale weighing. This analogy allows us to implement a novel “counting scale” termed LibraNet. Our idea is that, by placing a crowd image on the scale, LibraNet (agent) learns to place appropriate weights to match the count: at each step, one weight (action) is chosen from the weight box (the predefined action pool) conditioned on the image features and the placed weights (state) until the pointer (the agent output) informs balance. We investigate two forms of state definition and explore four types of LibraNet implementations under different learning paradigms, including deep Q-network (DQN), actor-critic (AC), imitation learning (IL), and mixed AC+IL. Experiments show that LibraNet indeed mimics scale weighing, that it outperforms or performs comparably against state-of-the-art approaches on five crowd counting benchmarks, that it can be used as a plug-in to improve off-the-shelf counting models, and particularly that it demonstrates remarkable cross-dataset generalization. Code and models are available at https://git.io/libranet.


  • TasselNetV3: Explainable Plant Counting With Guided Upsampling and Background Suppression

    by Hao Lu, Liang Liu, Ya-Nan Li, Xiao-Ming Zhao, Xi-Qing Wang, Zhi-Guo Cao

    Fast and accurate plant counting tools affect revolution in modern agriculture. Agricultural practitioners, however, expect the output of the tools to be not only accurate but also explainable. Such explainability often refers to the ability to infer which instance is counted. One intuitive way is to generate a bounding box for each instance. Nevertheless, compared with counting by detection, plant counts can be inferred more directly in the local count framework, while one thing reproaching this paradigm is its poor explainability of output visualization. In particular, we find that the poor explainability becomes a bottleneck limiting the counting performance. To address this, we explore the idea of guided upsampling and background suppression where a novel upsampling operator is proposed to allow count redistribution, and segmentation decoders with different fusion strategies are investigated to suppress background, respectively. By integrating them into our previous counting model TasselNetV2, we introduce TasselNetV3 series: TasselNetV3-Lite and TasselNetV3-Seg. We validate the TasselNetV3 series on three public plant counting data sets and a new unmanned aircraft vehicle (UAV)-based data set, covering maize tassels counting, wheat ears counting, and rice plants counting. Extensive results show that guided upsampling and background suppression not only improve counting performance but also enable explainable visualization. Aside from state-of-the-art performance, we have several interesting observations: 1) a limited-receptive-field counter in most cases outperforms a large-receptive-field one; 2) it is sufficient to generate empirical segmentation masks from dotted annotations; 3) middle fusion is a good choice to integrate foreground–background a priori knowledge; and 4) decoupling the learning of counting and segmentation matters.


  • NSSNet: Scale-Aware Object Counting With Non-Scale Suppression

    by Liang Liu, Zhiguo Cao, Hao Lu, Haipeng Xiong, Chunhua Shen

    In object counting, objects often exhibit different sizes at different scales, even if they have similar physical sizes in reality. This is particularly true when targeting crowd counting and vehicle counting in intelligent transportation. Failing to model such variations leads to the mismatch between the object size and image scale. To address this problem, existing methods often extract multi-scale features, but they either still generate the single-scale prediction or lack an explicit suppression mechanism to eliminate predictions engendered by inappropriate scales. Our scale analysis manifests that, the single-scale estimation only works well for objects of certain sizes, and a suppression operator is required to isolate the estimation of a specific scale. In this work, we propose a scale-aware counting network termed NSSNet. NSSNet has two key features: it not only i) generates multi-scale predictions but also ii) applies a novel non-scale suppression (NSS) operator to suppress scale-mismatched estimations. NSS is inspired by the widely-used non-maximum suppression (NMS). In contrast to NMS that only reserves the maximum response, NSS filters out those clearly wrong predictions (the remaining predictions may still be from multiple scales). We evaluate NSSNet on four standard crowd and vehicle counting benchmarks and report state-of-the-art performance. We also show the scale adaptability of NSSNet through a controlled multi-scale experiment. Code and pretrained models are available at https://git.io/nssnet.


  • Open Access

    From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

    by Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Chunhua Shen, Zhiguo Cao

    Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, inf) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property---spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance. Code and models are available at: https://tinyurl.com/SS-DCNet.

  • Open Access

    High-Throughput Rice Density Estimation from Transplantation to Tillering Stages Using Deep Networks

    by Liang Liu, Hao Lu, Yanan Li, Zhiguo Cao

    Rice density is closely related to yield estimation, growth diagnosis, cultivated area statistics, and management and damage evaluation. Currently, rice density estimation heavily relies on manual sampling and counting, which is inefficient and inaccurate. With the prevalence of digital imagery, computer vision (CV) technology emerges as a promising alternative to automate this task. However, challenges of an in-field environment, such as illumination, scale, and appearance variations, render gaps for deploying CV methods. To fill these gaps towards accurate rice density estimation, we propose a deep learning-based approach called the Scale-Fusion Counting Classification Network (SFC2Net) that integrates several state-of-the-art computer vision ideas. In particular, SFC2Net addresses appearance and illumination changes by employing a multicolumn pretrained network and multilayer feature fusion to enhance feature representation. To ameliorate sample imbalance engendered by scale, SFC2Net follows a recent blockwise classification idea. We validate SFC2Net on a new rice plant counting (RPC) dataset collected from two field sites in China from 2010 to 2013. Experimental results show that SFC2Net achieves highly accurate counting performance on the RPC dataset with a mean absolute error (MAE) of 25.51, a root mean square error (MSE) of 38.06, a relative MAE of 3.82%, and a of 0.98, which exhibits a relative improvement of 48.2% w.r.t. MAE over the conventional counting approach CSRNet. Further, SFC2Net provides high-throughput processing capability, with 16.7 frames per second on images. Our results suggest that manual rice counting can be safely replaced by SFC2Net at early growth stages. Code and models are available online at https://git.io/sfc2net.


  • Open Access

    TasselNetv2: in-field counting of wheat spikes with context-augmented local regression networks

    by Haipeng Xiong, Zhiguo Cao, Hao Lu, Simon Madec, Liang Liu, Chunhua Shen

    Background: Grain yield of wheat is greatly associated with the population of wheat spikes, i.e., $$spike~number~\text {m}^{-2}$$spikenumberm-2 . To obtain this index in a reliable and efficient way, it is necessary to count wheat spikes accurately and automatically. Currently computer vision technologies have shown great potential to automate this task effectively in a low-end manner. In particular, counting wheat spikes is a typical visual counting problem, which is substantially studied under the name of object counting in Computer Vision. TasselNet, which represents one of the state-of-the-art counting approaches, is a convolutional neural network-based local regression model, and currently benchmarks the best record on counting maize tassels. However, when applying TasselNet to wheat spikes, it cannot predict accurate counts when spikes partially present. Results: In this paper, we make an important observation that the counting performance of local regression networks can be significantly improved via adding visual context to the local patches. Meanwhile, such context can be treated as part of the receptive field without increasing the model capacity. We thus propose a simple yet effective contextual extension of TasselNet—TasselNetv2. If implementing TasselNetv2 in a fully convolutional form, both training and inference can be greatly sped up by reducing redundant computations. In particular, we collected and labeled a large-scale wheat spikes counting (WSC) dataset, with 1764 high-resolution images and 675,322 manually-annotated instances. Extensive experiments show that, TasselNetv2 not only achieves state-of-the-art performance on the WSC dataset ( $$91.01\%$$91.01% counting accuracy) but also is more than an order of magnitude faster than TasselNet (13.82 fps on $$912\times 1216$$912×1216 images). The generality of TasselNetv2 is further demonstrated by advancing the state of the art on both the Maize Tassels Counting and ShanghaiTech Crowd Counting datasets. Conclusions: This paper describes TasselNetv2 for counting wheat spikes, which simultaneously addresses two important use cases in plant counting: improving the counting accuracy without increasing model capacity, and improving efficiency without sacrificing accuracy. It is promising to be deployed in a real-time system with high-throughput demand. In particular, TasselNetv2 can achieve sufficiently accurate results when training from scratch with small networks, and adopting larger pre-trained networks can further boost accuracy. In practice, one can trade off the performance and efficiency according to certain application scenarios. Code and models are made available at: https://tinyurl.com/TasselNetv2.


  • Counting Objects by Blockwise Classification

    by Liang Liu, Hao Lu, Haipeng Xiong, Ke Xian, Zhiguo Cao, Chunhua Shen

    In this paper, we introduce the idea of blockwise classification to count objects. The current mainstream method for counting objects is to regress the density map or to regress the redundant count map via a deep convolutional neural network (CNN). However, these methods suffer from two critical issues: inaccurately generated regression targets and serious sample imbalances. First, the ground truth density map is generated by convolving the dot map using a Gaussian kernel. Because an inappropriate kernel can cover the background or uncover objects, this approach introduces a form of noise, and therefore results in ambiguities when training the networks. Second, inhomogeneously distributed objects often exist in images, which gives rise to a data collection bias. This leads to a long-tailed distribution of region counts, which is a typical characteristic that occurs with imbalanced samples; therefore, underestimations in high-density regions and overestimations in low-density regions are common. In this paper, we address these two issues within one framework—blockwise count level classification. The intuition behind this idea is that while it may not be possible to provide an exact count of pixels or patches, it is possible to provide a count of a region that falls within a certain interval with high confidence. Our method classifies the count levels of each block produced by nonlinearly quantizing the continuous counts, thus transforming the imbalance of sample patch counts into a class imbalance of count levels. Consequently, an information-entropy-inspired loss can be applied to alleviate this issue. Through ablative studies, we analyze the impact of imbalanced data, Gaussian kernel sizes, quantization errors, and the effectiveness of each module in our method. Without bells and whistles, our method outperforms or performs competitively with other state-of-the-art approaches on seven object-counting benchmarks, including four crowd-counting datasets from ShanghaiTech, WorldExpo’10, UCF-QNRF and UCF_CC_50, one vehicle-counting dataset (TRANCOS), one maize-tassel-counting dataset (MTC), and one challenging sonar fish-counting dataset that we constructed. The results suggest that our framework provides a strong and improved baseline for object counting.