Deep Constrained Siamese Hash Coding Network and Load-Balanced Locality-Sensitive Hashing for Near Duplicate Image Detection

Analysis of the ISIC image datasets: Usage, benchmarks and recommendations

The International Skin Imaging Collaboration (ISIC) datasets have become a leading repository for researchers in machine learning for medical image analysis, especially in the field of skin cancer detection and malignancy assessment. They contain tens of thousands of dermoscopic photographs together with gold-standard lesion diagnosis metadata. The associated yearly challenges have resulted in major contributions to the field, with papers reporting measures well in excess of human experts. Skin cancers can be divided into two major groups - melanoma and non-melanoma. Although less prevalent, melanoma is considered to be more serious as it can quickly spread to other organs if not treated at an early stage. In this paper, we summarise the usage of the ISIC dataset images and present an analysis of yearly releases over a period of 2016 - 2020. Our analysis found a significant number of duplicate images, both within and between the datasets. Additionally, we also noted duplicates spread across testing and training sets. Due to these irregularities, we propose a duplicate removal strategy and recommend a curated dataset for researchers to use when working on ISIC datasets. Given that ISIC 2020 focused on melanoma classification, we conduct experiments to provide benchmark results on the ISIC 2020 test set, with additional analysis on the smaller ISIC 2017 test set. Testing was completed following the application of our duplicate removal strategy and an additional data balancing step. As a result of removing 14,310 duplicate images from the training set, our benchmark results show good levels of melanoma prediction with an AUC of 0.80 for the best performing model. As our aim was not to maximise network performance, we did not include additional steps in our experiments. Finally, we provide recommendations for future research by highlighting irregularities that may present research challenges. A list of image files with reference to the original ISIC dataset sources for the recommended curated training set will be shared on our GitHub repository (available at www.github.com/mmu-dermatology-research/isic_duplicate_removal_strategy).

Video Text Tracking With a Spatio-Temporal Complementary Model

Text tracking is to track multiple texts in a video, and construct a trajectory for each text. Existing methods tackle this task by utilizing the tracking-by-detection framework, i.e., detecting the text instances in each frame and associating the corresponding text instances in consecutive frames. We argue that the tracking accuracy of this paradigm is severely limited in more complex scenarios, e.g., owing to motion blur, etc., the missed detection of text instances causes the break of the text trajectory. In addition, different text instances with similar appearance are easily confused, leading to the incorrect association of the text instances. To this end, a novel spatio-temporal complementary text tracking model is proposed in this paper. We leverage a Siamese Complementary Module to fully exploit the continuity characteristic of the text instances in the temporal dimension, which effectively alleviates the missed detection of the text instances, and hence ensures the completeness of each text trajectory. We further integrate the semantic cues and the visual cues of the text instance into a unified representation via a text similarity learning network, which supplies a high discriminative power in the presence of text instances with similar appearance, and thus avoids the mis-association between them. Our method achieves state-of-the-art performance on several public benchmarks. The source code is available at https://github.com/lsabrinax/VideoTextSCM.

Strongly Constrained Discrete Hashing

Learning to hash is a fundamental technique widely used in large-scale image retrieval. Most existing methods for learning to hash address the involved discrete optimization problem by the continuous relaxation of the binary constraint, which usually lead to large quantization errors and consequently suboptimal binary codes. A few discrete hashing methods have emerged recently. However, they either completely ignore some useful constraints (specifically the balance and decorrelation of hash bits) or just turn those constraints into regularizers that would make the optimization easier but less accurate. In this paper, we propose a novel supervised hashing method named, Strongly Constrained Discrete Hashing (SCDH), which overcomes such limitations. It can learn the binary codes for all examples in the training set, and meanwhile obtain a hash function for unseen samples with the above mentioned constraints preserved. Although the model of SCDH is fairly sophisticated, we are able to find closed-form solutions to all of its optimization subproblems and thus design an efficient algorithm that converges quickly. In addition, we extend SCDH to a kernelized version SCDHK. Our experiments on three large benchmark datasets have demonstrated that not only can SCDH and SCDHK achieve substantially higher MAP scores than state-of-the-art baselines, but they run much faster than those that are also supervised as well.