UH Biocomputation Group - Minghua Zheng

Few-shot Object Counting with Similarity-Aware Feature Enhancement

2023-06-27T16:26:27+01:00

On this week's Journal Club session, Minghua Zheng will talk about the paper entitled "Few-shot Object Counting with Similarity-Aware Feature Enhancement".

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i.e., described by one or several support images) occurring in the query image. The major challenge lies in that the target objects can be densely packed in the query image, making it hard to recognize every single one. To tackle the obstacle, we propose a novel learning block, equipped with a similarity comparison module and a feature enhancement module. Concretely, given a support image and a query image, we first derive a score map by comparing their projected features at every spatial position. The score maps regarding all support images are collected together and normalized across both the exemplar dimension and the spatial dimensions, producing a reliable similarity map. We then enhance the query feature with the support features by employing the developed point- wise similarities as the weighting coefficients. Such a design encourages the model to inspect the query image by focusing more on the regions akin to the support images, leading to much clearer boundaries between different objects. Extensive experiments on various benchmarks and training setups suggest that we surpass the state-of-the-art methods by a sufficiently large margin. For instance, on a recent large-scale FSC-147 dataset, we surpass the state-of-the-art method by improving the mean absolute error from 22.08 to 14.32 (35%↑). Code has been released in https://github.com/zhiyuanyou/SAFECount.

Papers:

Z. You, K. Yang, W. Luo, X. Lu, L. Cui, X. Le, "Few-shot Object Counting with Similarity-Aware Feature Enhancement", 2023, 6304--6313

Date: 2023/06/30
Time: 14:00
Location: 2J124 & online

Learning To Count Everything

2022-02-09T11:19:02+00:00

This week on Journal Club session Minghua Zheng will talk about a paper "Learning To Count Everything".

Existing works on visual counting primarily focus on one specific category at a time, such as people, animals, and cells. In this paper, we are interested in counting everything, that is to count objects from any category given only a few annotated instances from that category. To this end, we pose counting as a few-shot regression task. To tackle this task, we present a novel method that takes a query image together with a few exemplar objects from the query image and predicts a density map for the presence of all objects of interest in the query image. We also present a novel adaptation strategy to adapt our network to any novel visual category at test time, using only a few exemplar objects from the novel category. We also introduce a dataset of 147 object categories containing over 6000 images that are suitable for the few-shot counting task. The images are annotated with two types of annotation, dots and bounding boxes, and they can be used for developing few-shot counting models. Experiments on this dataset shows that our method outperforms several state-of-the-art object detectors and few-shot counting approaches. Our code and dataset can be found at https://github.com/cvlab-stonybrook/LearningToCountEverything .

Papers:

V. Ranjan, U. Sharma, T. Nguyen, M. Hoai, "Learning To Count Everything", 2021, 2021 IEEE/CV Conference on Computer Vision and Pattern Recognition (CVPR), 3393--3402

Date: 2022/02/11
Time: 14:00
Location: online

Class-Balanced Loss Based on Effective Number of Samples

2021-06-02T11:10:58+01:00

This week on Journal Club session Minghua Zheng will talk about a paper "Class-Balanced Loss Based on Effective Number of Samples".

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of longtailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re- weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula (1-β^n)/(1-β), where n is the number of samples and β ∈ [0, 1) is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

Papers:

Y. Cui, M. Jia, T. Lin, Y. Song, S. Belongie, "Class-Balanced Loss Based on Effective Number of Samples", 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9260--9269

Date: 2021/06/04
Time: 14:00
Location: online

Bacterial colony counting with Convolutional Neural Networks in Digital Microbiology Imaging

2020-11-09T10:28:15+00:00

This week on Journal Club session Minghua Zheng will talk about the paper "Bacterial colony counting with Convolutional Neural Networks in Digital Microbiology Imaging".

Counting bacterial colonies on microbiological culture plates is a time-consuming, error-prone, nevertheless essential quantitative task in Clinica Microbiology Laboratories. With this work we explore the possibility to find effective solutions to the above issue by designing and testing two different machine learning approaches. The first one is based on the extraction of a complete set of handcrafted morphometric and radiometric features used within a Support Vector Machines solution. The second one is based on the design and configuration of a Convolutional Neural Networks deep learning architecture. To validate, in a real and challenging clinical scenario, the proposed bacterial load estimation techniques, we built and publicly released a fully labeled large and representative database of both single and aggregated bacterial colonies extracted from routine clinical laboratory culture plates. Dataset enhancement approaches have also been experimentally tested for performance optimization. The adopted deep learning approach outperformed the handcrafted feature based one, and also a conventional reference technique, by a large margin, becoming a preferable solution for the addressed Digital Microbiology Imaging quantification task, especially in the emerging context of Full Laboratory Automation systems.

Papers:

Alessandro Ferrari, Stefano Lombardia, Alberto Signoroni. (2017). "Bacterial colony counting with Convolutional Neural Networks inDigital Microbiology Imaging" , Pattern Recognition, Volume 61, January 2017, Pages 629-640

Date: 13/11/2020
Time: 16:00
Location: online