A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a multivariate Gaussian distribution and calculates the 2-Wasserstein distance based on their means and covariances. While FID effectively measures how closely synthetic data match real data in many image synthesis tasks, the primary goal in biomedical generative models is often to enrich training datasets ideally with corresponding annotations. For this purpose, the gold standard for evaluating generative models is to incorporate synthetic data into downstream task training, such as classification and segmentation, to pragmatically assess its performance. In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals in classification and segmentation. We highlight the limitations of using various metrics, represented by FID and its variants, as evaluation criteria for these applications and address their potential caveats in broader biomedical imaging modalities and downstream tasks.

Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos

Zebrafish are widely used in biomedical research and developmental stages of their embryos often need to be synchronized for further analysis. We present an unsupervised approach to extract descriptive features from 3D+t point clouds of zebrafish embryos and subsequently use those features to temporally align corresponding developmental stages. An autoencoder architecture is proposed to learn a descriptive representation of the point clouds and we designed a deep regression network for their temporal alignment. We achieve a high alignment accuracy with an average mismatch of only 3.83 minutes over an experimental duration of 5.3 hours. As a fully-unsupervised approach, there is no manual labeling effort required and unlike manual analyses the method easily scales. Besides, the alignment without human annotation of the data also avoids any influence caused by subjective bias.

No Free Lunch in Annotation either: An objective evaluation of foundation models for streamlining annotation in animal tracking

We analyze the capabilities of foundation models addressing the tedious task of generating annotations for animal tracking. Annotating a large amount of data is vital and can be a make-or-break factor for the robustness of a tracking model. Robustness is particularly crucial in animal tracking, as accurate tracking over long time horizons is essential for capturing the behavior of animals. However, generating additional annotations using foundation models can be counterproductive, as the quality of the annotations is just as important. Poorly annotated data can introduce noise and inaccuracies, ultimately compromising the performance and accuracy of the trained model. Over-reliance on automated annotations without ensuring precision can lead to diminished results, making careful oversight and quality control essential in the annotation process. Ultimately, we demonstrate that a thoughtful combination of automated annotations and manually annotated data is a valuable strategy, yielding an IDF1 score of 80.8 against blind usage of SAM2 video with an IDF1 score of 65.6.

LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction

Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applications such as industrial inspection, where logical anomaly detection is critical for maintaining high-quality standards and minimizing costly recalls. Previous research in anomaly detection (AD) has relied on prior knowledge for designing algorithms, which often requires extensive manual annotations, significant computing power, and large amounts of data for training. Autoregressive, multimodal Vision Language Models (AVLMs) offer a promising alternative due to their exceptional performance in visual reasoning across various domains. Despite this, their application to logical AD remains unexplored. In this work, we investigate using AVLMs for logical AD and demonstrate that they are well-suited to the task. Combining AVLMs with format embedding and a logic reasoner, we achieve SOTA performance on public benchmarks, MVTec LOCO AD, with an AUROC of 86.0% and F1-max of 83.7%, along with explanations of anomalies. This significantly outperforms the existing SOTA method by a large margin.

Effortless Efficiency: Low-Cost Pruning of Diffusion Models

Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising inference costs, and causing environmental impact. While some studies have explored pruning techniques to improve the memory efficiency of diffusion models, most existing methods require extensive retraining to retain the model performance. Retraining a modern large diffusion model is extremely costly and resource-intensive, which limits the practicality of these methods. In this work, we achieve low-cost diffusion pruning without retraining by proposing a model-agnostic structural pruning framework for diffusion models that learns a differentiable mask to sparsify the model. To ensure effective pruning that preserves the quality of the final denoised latent, we design a novel end-to-end pruning objective that spans the entire diffusion process. As end-to-end pruning is memory-intensive, we further propose time step gradient checkpointing, a technique that significantly reduces memory usage during optimization, enabling end-to-end pruning within a limited memory budget. Results on state-of-the-art U-Net diffusion models SDXL and diffusion transformers (FLUX) demonstrate that our method can effectively prune up to 20% parameters with minimal perceptible performance degradation, and notably, without the need for model retraining. We also showcase that our method can still prune on top of time step distilled diffusion models.

Cascaded Diffusion Models for 2D and 3D Microscopy Image Synthesis to Enhance Cell Segmentation

Automated cell segmentation in microscopy images is essential for biomedical research, yet conventional methods are labor-intensive and prone to error. While deep learning-based approaches have proven effective, they often require large annotated datasets, which are scarce due to the challenges of manual annotation. To overcome this, we propose a novel framework for synthesizing densely annotated 2D and 3D cell microscopy images using cascaded diffusion models. Our method synthesizes 2D and 3D cell masks from sparse 2D annotations using multi-level diffusion models and NeuS, a 3D surface reconstruction approach. Following that, a pretrained 2D Stable Diffusion model is finetuned to generate realistic cell textures and the final outputs are combined to form cell populations. We show that training a segmentation model with a combination of our synthetic data and real data improves cell segmentation performance by up to 9\% across multiple datasets. Additionally, the FID scores indicate that the synthetic data closely resembles real data. The code for our proposed approach will be available at https://github.com/ruveydayilmaz0/cascaded_diffusion.

Visual Fixation-Based Retinal Prosthetic Simulation

This study proposes a retinal prosthetic simulation framework driven by visual fixations, inspired by the saccade mechanism, and assesses performance improvements through end-to-end optimization in a classification task. Salient patches are predicted from input images using the self-attention map of a vision transformer to mimic visual fixations. These patches are then encoded by a trainable U-Net and simulated using the pulse2percept framework to predict visual percepts. By incorporating a learnable encoder, we aim to optimize the visual information transmitted to the retinal implant, addressing both the limited resolution of the electrode array and the distortion between the input stimuli and resulting phosphenes. The predicted percepts are evaluated using the self-supervised DINOv2 foundation model, with an optional learnable linear layer for classification accuracy. On a subset of the ImageNet validation set, the fixation-based framework achieves a classification accuracy of 87.72%, using computational parameters based on a real subject's physiological data, significantly outperforming the downsampling-based accuracy of 40.59% and approaching the healthy upper bound of 92.76%. Our approach shows promising potential for producing more semantically understandable percepts with the limited resolution available in retinal prosthetics.

Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields

The segmentation and tracking of living cells play a vital role within the biomedical domain, particularly in cancer research, drug development, and developmental biology. These are usually tedious and time-consuming tasks that are traditionally done by biomedical experts. Recently, to automatize these processes, deep learning based segmentation and tracking methods have been proposed. These methods require large-scale datasets and their full potential is constrained by the scarcity of annotated data in the biomedical imaging domain. To address this limitation, we propose Biomedical Video Diffusion Model (BVDM), capable of generating realistic-looking synthetic microscopy videos. Trained only on a single real video, BVDM can generate videos of arbitrary length with pixel-level annotations that can be used for training data-hungry models. It is composed of a denoising diffusion probabilistic model (DDPM) generating high-fidelity synthetic cell microscopy images and a flow prediction model (FPM) predicting the non-rigid transformation between consecutive video frames. During inference, initially, the DDPM imposes realistic cell textures on synthetic cell masks which are generated based on real data statistics. The flow prediction model predicts the flow field between consecutive masks and applies that to the DDPM output from the previous time frame to create the next one while keeping temporal consistency. BVDM outperforms state-of-the-art synthetic live cell microscopy video generation models. Furthermore, we demonstrate that a sufficiently large synthetic dataset enhances the performance of cell segmentation and tracking models compared to using a limited amount of available real data.

Optimizing Retinal Prosthetic Stimuli with Conditional Invertible Neural Networks

Implantable retinal prostheses offer a promising solution to restore partial vision by circumventing damaged photoreceptor cells in the retina and directly stimulating the remaining functional retinal cells. However, the information transmission between the camera and retinal cells is often limited by the low resolution of the electrode array and the lack of specificity for different ganglion cell types, resulting in suboptimal stimulations. In this work, we propose to utilize normalizing flow-based conditional invertible neural networks to optimize retinal implant stimulation in an unsupervised manner. The invertibility of these networks allows us to use them as a surrogate for the computational model of the visual system, while also encoding input camera signals into optimized electrical stimuli on the electrode array. Compared to other methods, such as trivial downsampling, linear models, and feed-forward convolutional neural networks, the flow-based invertible neural network and its conditional extension yield better visual reconstruction qualities w.r.t. various metrics using a physiologically validated simulation tool.

Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time

Automated vehicles require an accurate perception of their surroundings for safe and efficient driving. Lidar-based object detection is a widely used method for environment perception, but its performance is significantly affected by adverse weather conditions such as rain and fog. In this work, we investigate various strategies for enhancing the robustness of lidar-based object detection by processing sequential data samples generated by lidar sensors. Our approaches leverage temporal information to improve a lidar object detection model, without the need for additional filtering or pre-processing steps. We compare $10$ different neural network architectures that process point cloud sequences including a novel augmentation strategy introducing a temporal offset between frames of a sequence during training and evaluate the effectiveness of all strategies on lidar point clouds under adverse weather conditions through experiments. Our research provides a comprehensive study of effective methods for mitigating the effects of adverse weather on the reliability of lidar-based object detection using sequential data that are evaluated using public datasets such as nuScenes, Dense, and the Canadian Adverse Driving Conditions Dataset. Our findings demonstrate that our novel method, involving temporal offset augmentation through randomized frame skipping in sequences, enhances object detection accuracy compared to both the baseline model (Pillar-based Object Detection) and no augmentation.