PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?

The image-to-image translation abilities of generative learning models have recently made significant progress in the estimation of complex (steered) mappings between image distributions. While appearance based tasks like image in-painting or style transfer have been studied at length, we propose to investigate the potential of generative models in the context of physical simulations. Providing a dataset of 300k image-pairs and baseline evaluations for three different physical simulation tasks, we propose a benchmark to investigate the following research questions: i) are generative models able to learn complex physical relations from input-output image pairs? ii) what speedups can be achieved by replacing differential equation based simulations? While baseline evaluations of different current models show the potential for high speedups (ii), these results also show strong limitations toward the physical correctness (i). This underlines the need for new methods to enforce physical correctness. Data, baseline models and evaluation code http://www.physics-gen.org.

Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach

In this paper, we present an approach for evaluating attribution maps, which play a central role in interpreting the predictions of convolutional neural networks (CNNs). We show that the widely used insertion/deletion metrics are susceptible to distribution shifts that affect the reliability of the ranking. Our method proposes to replace pixel modifications with adversarial perturbations, which provides a more robust evaluation framework. By using smoothness and monotonicity measures, we illustrate the effectiveness of our approach in correcting distribution shifts. In addition, we conduct the most comprehensive quantitative and qualitative assessment of attribution maps to date. Introducing baseline attribution maps as sanity checks, we find that our metric is the only contender to pass all checks. Using Kendall's $\tau$ rank correlation coefficient, we show the increased consistency of our metric across 15 dataset-architecture combinations. Of the 16 attribution maps tested, our results clearly show SmoothGrad to be the best map currently available. This research makes an important contribution to the development of attribution maps by providing a reliable and consistent evaluation framework. To ensure reproducibility, we will provide the code along with our results.

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images

Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically designed for microscopic wood fiber analysis. Our approach adapts the YOLO architecture to address the challenges posed by large, high-resolution microscopy images and the need for high recall in localization of the cell type of interest (vessel elements). Our results show that WoodYOLO significantly outperforms state-of-the-art models, achieving performance gains of 12.9% and 6.5% in F2 score over YOLOv10 and YOLOv7, respectively. This improvement in automated wood cell type localization capabilities contributes to enhancing regulatory compliance, supporting sustainable forestry practices, and promoting biodiversity conservation efforts globally.

How Do Training Methods Influence the Utilization of Vision Models?

Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values with little to no impact on the model's decisions. We revisit earlier studies that examined how architecture and task complexity influence this phenomenon and ask: is this phenomenon also affected by how we train the model? We conducted experimental evaluations on a diverse set of ImageNet-1k classification models to explore this, keeping the architecture and training data constant but varying the training pipeline. Our findings reveal that the training method strongly influences which layers become critical to the decision function for a given task. For example, improved training regimes and self-supervised training increase the importance of early layers while significantly under-utilizing deeper layers. In contrast, methods such as adversarial training display an opposite trend. Our preliminary results extend previous findings, offering a more nuanced understanding of the inner mechanics of neural networks. Code: https://github.com/paulgavrikov/layer_criticality

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation

This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size of the learned feature representation, our method forces the network to focus on the most salient image regions, effectively reducing background influence. Using adversarial attacks and the Effective Receptive Field, we show that Top-GAP directs more attention towards object pixels rather than the background. This leads to enhanced interpretability and robustness. We achieve over 50% robust accuracy on CIFAR-10 with PGD $\epsilon=\frac{8}{255}$ and $20$ iterations while maintaining the original clean accuracy. Furthermore, we see increases of up to 5% accuracy against distribution shifts. Our approach also yields more precise object localization, as evidenced by up to 25% improvement in Intersection over Union (IOU) compared to methods like GradCAM and Recipro-CAM.

Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail

Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and (mostly supervised) object classification. However, the recent advances in vision Foundation Models [25] and Vision Language Models (VLMs) [23] raise the question if these custom trained, multi-step approaches can be replaced with pre-trained, single-step VLMs. This paper analyzes the performance and limits of various VLMs in the context of VQA and OCR [5, 9, 12] tasks in a production-level scenario. Using data from the Retail-786k [10] dataset, we investigate the capabilities of pre-trained VLMs to answer detailed questions about advertised products in images. Our study includes two commercial models, GPT-4V [16] and GPT-4o [17], as well as four open-source models: InternVL [5], LLaVA 1.5 [12], LLaVA-NeXT [13], and CogAgent [9]. Our initial results show, that there is in general no big performance gap between open-source and commercial models. However, we observe a strong task dependent variance in VLM performance: while most models are able to answer questions regarding the product brand and price with high accuracy, they completely fail at the same time to correctly identity the specific product name or discount. This indicates the problem of VLMs to solve fine-grained classification tasks as well to model the more abstract concept of discounts.

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration

Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively. Data aggregation as well as high-resolution image generation both usually come at the risk of involving aliases, i.e.~standard architectures put their ability to reconstruct the model input in jeopardy to reach high PSNR values on validation data. The price to be paid is low model robustness. In this work, we show that simply providing alias-free paths in state-of-the-art reconstruction transformers supports improved model robustness at low costs on the restoration performance. We do so by proposing BOA-Restormer, a transformer-based image restoration model that executes downsampling and upsampling operations partly in the frequency domain to ensure alias-free paths along the entire model while potentially preserving all relevant high-frequency information.

Ambiguous Annotations: When is a Pedestrian not a Pedestrian?

Datasets labelled by human annotators are widely used in the training and testing of machine learning models. In recent years, researchers are increasingly paying attention to label quality. However, it is not always possible to objectively determine whether an assigned label is correct or not. The present work investigates this ambiguity in the annotation of autonomous driving datasets as an important dimension of data quality. Our experiments show that excluding highly ambiguous data from the training improves model performance of a state-of-the-art pedestrian detector in terms of LAMR, precision and F1 score, thereby saving training time and annotation costs. Furthermore, we demonstrate that, in order to safely remove ambiguous instances and ensure the retained representativeness of the training data, an understanding of the properties of the dataset and class under investigation is crucial.

Can Biases in ImageNet Models Explain Generalization?

The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning methods. For image classification, this manifests in the existence of adversarial attacks, the performance drops on distorted images, and a lack of generalization to concepts such as sketches. The current understanding of generalization in neural networks is very limited, but some biases that differentiate models from human vision have been identified and might be causing these limitations. Consequently, several attempts with varying success have been made to reduce these biases during training to improve generalization. We take a step back and sanity-check these attempts. Fixing the architecture to the well-established ResNet-50, we perform a large-scale study on 48 ImageNet models obtained via different training methods to understand how and if these biases - including shape bias, spectral biases, and critical bands - interact with generalization. Our extensive study results reveal that contrary to previous findings, these biases are insufficient to accurately predict the generalization of a model holistically. We provide access to all checkpoints and evaluation code at https://github.com/paulgavrikov/biases_vs_generalization

Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets

The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the GenImage dataset, we demonstrate that detectors indeed learn from these undesired factors. Furthermore, we show that removing the named biases substantially increases robustness to JPEG compression and significantly alters the cross-generator performance of evaluated detectors. Specifically, it leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors on the GenImage dataset, achieving state-of-the-art results. We provide the dataset and source codes of this paper on the anonymous website: https://www.unbiased-genimage.org