DGD-cGAN: A Dual Generator for Image Dewatering and Restoration

Underwater images are usually covered with a blue-greenish colour cast, making them distorted, blurry or low in contrast. This phenomenon occurs due to the light attenuation given by the scattering and absorption in the water column. In this paper, we present an image enhancement approach for dewatering which employs a conditional generative adversarial network (cGAN) with two generators. Our Dual Generator Dewatering cGAN (DGD-cGAN) removes the haze and colour cast induced by the water column and restores the true colours of underwater scenes whereby the effects of various attenuation and scattering phenomena that occur in underwater images are tackled by the two generators. The first generator takes at input the underwater image and predicts the dewatered scene, while the second generator learns the underwater image formation process by implementing a custom loss function based upon the transmission and the veiling light components of the image formation model. Our experiments show that DGD-cGAN consistently delivers a margin of improvement as compared with the state-of-the-art methods on several widely available datasets.

TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation

Deep learning methods typically depend on the availability of labeled data, which is expensive and time-consuming to obtain. Active learning addresses such effort by prioritizing which samples are best to annotate in order to maximize the performance of the task model. While frameworks for active learning have been widely explored in the context of classification of natural images, they have been only sparsely used in medical image segmentation. The challenge resides in obtaining an uncertainty measure that reveals the best candidate data for annotation. This paper proposes Test-time Augmentation for Active Learning (TAAL), a novel semi-supervised active learning approach for segmentation that exploits the uncertainty information offered by data transformations. Our method applies cross-augmentation consistency during training and inference to both improve model learning in a semi-supervised fashion and identify the most relevant unlabeled samples to annotate next. In addition, our consistency loss uses a modified version of the JSD to further improve model performance. By relying on data transformations rather than on external modules or simple heuristics typically used in uncertainty-based strategies, TAAL emerges as a simple, yet powerful task-agnostic semi-supervised active learning approach applicable to the medical domain. Our results on a publicly-available dataset of cardiac images show that TAAL outperforms existing baseline methods in both fully-supervised and semi-supervised settings. Our implementation is publicly available on https://github.com/melinphd/TAAL.

HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery

Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from image-mesh misalignment, resulting in inaccurate reconstruction. In contrast, 3D keypoint estimation methods utilize the volumetric representation to achieve pixel-level accuracy but may predict unrealistic body structures. To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework. HybrIK directly transforms accurate 3D joints to body-part rotations via twist-and-swing decomposition. The swing rotations are analytically solved with 3D joints, while the twist rotations are derived from visual cues through neural networks. To capture comprehensive whole-body details, we further develop a holistic framework, HybrIK-X, which enhances HybrIK with articulated hands and an expressive face. HybrIK-X is fast and accurate by solving the whole-body pose with a one-stage model. Experiments demonstrate that HybrIK and HybrIK-X preserve both the accuracy of 3D joints and the realistic structure of the parametric human model, leading to pixel-aligned whole-body mesh recovery. The proposed method significantly surpasses the state-of-the-art methods on various benchmarks for body-only, hand-only, and whole-body scenarios. Code and results can be found at https://jeffli.site/HybrIK-X/

CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks

Contrastive Language-Image Pre-training (CLIP) is a powerful multimodal large vision model that has demonstrated significant benefits for downstream tasks, including many zero-shot learning and text-guided vision tasks. However, we notice some severe problems regarding the model's explainability, which undermines its credibility and impedes related tasks. Specifically, we find CLIP prefers the background regions than the foregrounds according to the predicted similarity map, which contradicts human understanding. Besides, there are obvious noisy activations on the visualization results at irrelevant positions. To address these two issues, we conduct in-depth analyses and reveal the reasons with new findings and evidences. Based on these insights, we propose the CLIP Surgery, a method that enables surgery-like modifications for the inference architecture and features, for better explainability and enhancement in multiple open-vocabulary tasks. The proposed method has significantly improved the explainability of CLIP for both convolutional networks and vision transformers, surpassing existing methods by large margins. Besides, our approach also demonstrates remarkable improvements in open-vocabulary segmentation and multi-label recognition tasks. For examples, the mAP improvement on NUS-Wide multi-label recognition is 4.41% without any additional training, and our CLIP Surgery surpasses the state-of-the-art method by 8.74% at mIoU on Cityscapes open-vocabulary semantic segmentation. Furthermore, our method benefits other tasks including multimodal visualization and interactive segmentation like Segment Anything Model (SAM). The code is available at https://github.com/xmed-lab/CLIP_Surgery

A priori compression of convolutional neural networks for wave simulators

Convolutional neural networks are now seeing widespread use in a variety of fields, including image classification, facial and object recognition, medical imaging analysis, and many more. In addition, there are applications such as physics-informed simulators in which accurate forecasts in real time with a minimal lag are required. The present neural network designs include millions of parameters, which makes it difficult to install such complex models on devices that have limited memory. Compression techniques might be able to resolve these issues by decreasing the size of CNN models that are created by reducing the number of parameters that contribute to the complexity of the models. We propose a compressed tensor format of convolutional layer, a priori, before the training of the neural network. 3-way kernels or 2-way kernels in convolutional layers are replaced by one-way fiters. The overfitting phenomena will be reduced also. The time needed to make predictions or time required for training using the original Convolutional Neural Networks model would be cut significantly if there were fewer parameters to deal with. In this paper we present a method of a priori compressing convolutional neural networks for finite element (FE) predictions of physical data. Afterwards we validate our a priori compressed models on physical data from a FE model solving a 2D wave equation. We show that the proposed convolutinal compression technique achieves equivalent performance as classical convolutional layers with fewer trainable parameters and lower memory footprint.

Auto-Focus Contrastive Learning for Image Manipulation Detection

Generally, current image manipulation detection models are simply built on manipulation traces. However, we argue that those models achieve sub-optimal detection performance as it tends to: 1) distinguish the manipulation traces from a lot of noisy information within the entire image, and 2) ignore the trace relations among the pixels of each manipulated region and its surroundings. To overcome these limitations, we propose an Auto-Focus Contrastive Learning (AF-CL) network for image manipulation detection. It contains two main ideas, i.e., multi-scale view generation (MSVG) and trace relation modeling (TRM). Specifically, MSVG aims to generate a pair of views, each of which contains the manipulated region and its surroundings at a different scale, while TRM plays a role in modeling the trace relations among the pixels of each manipulated region and its surroundings for learning the discriminative representation. After learning the AF-CL network by minimizing the distance between the representations of corresponding views, the learned network is able to automatically focus on the manipulated region and its surroundings and sufficiently explore their trace relations for accurate manipulation detection. Extensive experiments demonstrate that, compared to the state-of-the-arts, AF-CL provides significant performance improvements, i.e., up to 2.5%, 7.5%, and 0.8% F1 score, on CAISA, NIST, and Coverage datasets, respectively.

RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training

Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedical VQA suffers from limited data. In this paper, we propose a retrieval-augmented pretrain-and-finetune paradigm named RAMM for biomedical VQA to overcome the data limitation issue. Specifically, we collect a new biomedical dataset named PMCPM which offers patient-based image-text pairs containing diverse patient situations from PubMed. Then, we pretrain the biomedical multi-modal model to learn visual and textual representation for image-text pairs and align these representations with image-text contrastive objective (ITC). Finally, we propose a retrieval-augmented method to better use the limited data. We propose to retrieve similar image-text pairs based on ITC from pretraining datasets and introduce a novel retrieval-attention module to fuse the representation of the image and the question with the retrieved images and texts. Experiments demonstrate that our retrieval-augmented pretrain-and-finetune paradigm obtains state-of-the-art performance on Med-VQA2019, Med-VQA2021, VQARAD, and SLAKE datasets. Further analysis shows that the proposed RAMM and PMCPM can enhance biomedical VQA performance compared with previous resources and methods. We will open-source our dataset, codes, and pretrained model.

Unsupervised Domain Adaptation GAN Inversion for Image Editing

Existing GAN inversion methods work brilliantly for high-quality image reconstruction and editing while struggling with finding the corresponding high-quality images for low-quality inputs. Therefore, recent works are directed toward leveraging the supervision of paired high-quality and low-quality images for inversion. However, these methods are infeasible in real-world scenarios and further hinder performance improvement. In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing. Particularly, UDA-Inversion first regards the high-quality and low-quality images as the source domain and unlabeled target domain, respectively. Then, a discrepancy function is presented to measure the difference between two domains, after which we minimize the source error and the discrepancy between the distributions of two domains in the latent space to obtain accurate latent codes for low-quality images. Without direct supervision, constructive representations of high-quality images can be spontaneously learned and transformed into low-quality images based on unsupervised domain adaptation. Experimental results indicate that UDA-inversion is the first that achieves a comparable level of performance with supervised methods in low-quality images across multiple domain datasets. We hope this work provides a unique inspiration for latent embedding distributions in image process tasks.

AI-assisted Automated Workflow for Real-time X-ray Ptychography Data Analysis via Federated Resources

We present an end-to-end automated workflow that uses large-scale remote compute resources and an embedded GPU platform at the edge to enable AI/ML-accelerated real-time analysis of data collected for x-ray ptychography. Ptychography is a lensless method that is being used to image samples through a simultaneous numerical inversion of a large number of diffraction patterns from adjacent overlapping scan positions. This acquisition method can enable nanoscale imaging with x-rays and electrons, but this often requires very large experimental datasets and commensurately high turnaround times, which can limit experimental capabilities such as real-time experimental steering and low-latency monitoring. In this work, we introduce a software system that can automate ptychography data analysis tasks. We accelerate the data analysis pipeline by using a modified version of PtychoNN -- an ML-based approach to solve phase retrieval problem that shows two orders of magnitude speedup compared to traditional iterative methods. Further, our system coordinates and overlaps different data analysis tasks to minimize synchronization overhead between different stages of the workflow. We evaluate our workflow system with real-world experimental workloads from the 26ID beamline at Advanced Photon Source and ThetaGPU cluster at Argonne Leadership Computing Resources.

FREDSR: Fourier Residual Efficient Diffusive GAN for Single Image Super Resolution

FREDSR is a GAN variant that aims to outperform traditional GAN models in specific tasks such as Single Image Super Resolution with extreme parameter efficiency at the cost of per-dataset generalizeability. FREDSR integrates fast Fourier transformation, residual prediction, diffusive discriminators, etc to achieve strong performance in comparisons to other models on the UHDSR4K dataset for Single Image 3x Super Resolution from 360p and 720p with only 37000 parameters. The model follows the characteristics of the given dataset, resulting in lower generalizeability but higher performance on tasks such as real time up-scaling.