Yanhui Guo

Yanhui Guo, Fangzhou Luo, Shaoyuan Xu

For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). By explicitly modeling semantics information from a given reference image, SAIR is able to reliably restore severely degraded images not only to high-resolution and highly realistic looks but also to correct semantics. Quantitative and qualitative experiments collectively demonstrate the superior performance of the proposed SAIR. Our code is available at https://github.com/Liamkuo/SAIR.

Zhuoyi Yang, Ming Ding, Yanhui Guo et al.

In recent years, pretrained models revolutionized the paradigm of natural language understanding (NLU), where we append a randomly initialized classification head after the pretrained backbone, e.g. BERT, and finetune the whole model. As the pretrained backbone makes a major contribution to the improvement, we naturally expect a good pretrained classification head can also benefit the training. However, the final-layer output of the backbone, i.e. the input of the classification head, will change greatly during finetuning, making the usual head-only pretraining (LP-FT) ineffective. In this paper, we find that parameter-efficient tuning makes a good classification head, with which we can simply replace the randomly initialized heads for a stable performance gain. Our experiments demonstrate that the classification head jointly pretrained with parameter-efficient tuning consistently improves the performance on 9 tasks in GLUE and SuperGLUE.

Zheng Chen, Zongwei Wu, Eduard Zamfir et al.

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

Hengkang Wang, Yang Liu, Huidong Liu et al.

Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they suffer from approximation errors during reverse diffusion and insufficient temporal consistency. Moreover, dealing with 3D video data, VR is inherently computationally intensive. In this paper, we advocate viewing the reverse process in DMs as a function and present a novel Maximum a Posterior (MAP) framework that directly parameterizes video frames in the seed space of DMs, eliminating approximation errors. We also introduce strategies to promote bilevel temporal consistency: semantic consistency by leveraging clustering structures in the seed space, and pixel-level consistency by progressive warping with optical flow refinements. Extensive experiments on multiple virtual reality tasks demonstrate superior visual quality and temporal consistency achieved by our method compared to the state-of-the-art.

Dandan Chen Kaptur, Yue Huang, Xuejun Ryan Ji et al.

This research delved into GPT-4 and Kimi, two Large Language Models (LLMs), for systematic reviews. We evaluated their performance by comparing LLM-generated codes with human-generated codes from a peer-reviewed systematic review on assessment. Our findings suggested that the performance of LLMs fluctuates by data volume and question complexity for systematic reviews.

Binh M. Le, Shaoyuan Xu, Jinmiao Fu et al.

In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify query-specific regions in text-rich document images. Existing methods that directly inject queries into model layers by modifying the network architecture often struggle to adapt to new datasets with limited annotations. To address this, we introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder, leading to notable performance gains, particularly in data-scarce fine-tuning scenarios. Specifically, our approach introduces a dual-module framework: a query-aware module that generates a unique query vector to precisely guide the model's focus, as well as a query-agnostic module that captures the positional relationships among tokens, ensuring robust spatial understanding. Notably, both modules operate independently of the vision attention blocks, facilitating targeted learning of query embeddings and enhancing visual semantic identification. Experiments with OCR-free VLMs across multiple datasets demonstrate significant performance improvements using our method, especially in handling text-rich documents in data-scarce environments.

Rushabh Patel, Yanhui Guo

Background: The learning of genotype-phenotype associations and history of human disease by doing detailed and precise analysis of phenotypic abnormalities can be defined as deep phenotyping. To understand and detect this interaction between phenotype and genotype is a fundamental step when translating precision medicine to clinical practice. The recent advances in the field of machine learning is efficient to predict these interactions between abnormal human phenotypes and genes. Methods: In this study, we developed a framework to predict links between human phenotype ontology (HPO) and genes. The annotation data from the heterogeneous knowledge resources i.e., orphanet, is used to parse human phenotype-gene associations. To generate the embeddings for the nodes (HPO & genes), an algorithm called node2vec was used. It performs node sampling on this graph based on random walks, then learns features over these sampled nodes to generate embeddings. These embeddings were used to perform the downstream task to predict the presence of the link between these nodes using 5 different supervised machine learning algorithms. Results: The downstream link prediction task shows that the Gradient Boosting Decision Tree based model (LightGBM) achieved an optimal AUROC 0.904 and AUCPR 0.784. In addition, LightGBM achieved an optimal weighted F1 score of 0.87. Compared to the other 4 methods LightGBM is able to find more accurate interaction/link between human phenotype & gene pairs.

Yanhui Guo, Amira S. Ashour

Melanoma classification is a serious stage to identify the skin disease. It is considered a challenging process due to the intra-class discrepancy of melanomas, skin lesions low contrast, and the artifacts in the dermoscopy images, including noise, existence of hair, air bubbles, and the similarity between melanoma and non-melanoma cases. To solve these problems, we propose a novel multiple convolution neural network model (MCNN) to classify different seven disease types in dermoscopic images, where several models were trained separately using an additive sample learning strategy. The MCNN model is trained and tested using the training and validation sets from the International Skin Imaging Collaboration (ISIC 2018), respectively. The receiver operating characteristic (ROC) curve is used to evaluate the performance of the proposed method. The values of AUC (the area under the ROC curve) were used to evaluate the performance of the MCNN.