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

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

UH Biocomputation Group - categorization

Few-shot Object Counting with Similarity-Aware Feature Enhancement

Class-Balanced Loss Based on Effective Number of Samples