Dataset distillation aims to compress a dataset into a much smaller one so that a model trained on the distilled dataset achieves high accuracy. Current methods frame this as maximizing the distilled classification accuracy for a budget of K distilled images-per-class, where K is a positive integer. In this paper, we push the boundaries of dataset distillation, compressing the dataset into less than an image-per-class. It is important to realize that the meaningful quantity is not the number of distilled images-per-class but the number of distilled pixels-per-dataset. We therefore, propose Poster Dataset Distillation (PoDD), a new approach that distills the entire original dataset into a single poster. The poster approach motivates new technical solutions for creating training images and learnable labels. Our method can achieve comparable or better performance with less than an image-per-class compared to existing methods that use one image-per-class. Specifically, our method establishes a new state-of-the-art performance on CIFAR-10, CIFAR-100, and CUB200 using as little as 0.3 images-per-class.
The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning. This practice is considered safe, as no current method can recover the unsafe, pre-fine-tuning model weights. In this paper, we demonstrate that this assumption is often false. Concretely, we present Spectral DeTuning, a method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, our method aims to recover the exact pre-fine-tuning weights. Our approach exploits this new vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.
Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, very few works have done so for video editing. We present the first diffusion-based method that is able to perform text-based motion and appearance editing of general videos. Our approach uses a video diffusion model to combine, at inference time, the low-resolution spatio-temporal information from the original video with new, high resolution information that it synthesized to align with the guiding text prompt. As obtaining high-fidelity to the original video requires retaining some of its high-resolution information, we add a preliminary stage of finetuning the model on the original video, significantly boosting fidelity. We propose to improve motion editability by a new, mixed objective that jointly finetunes with full temporal attention and with temporal attention masking. We further introduce a new framework for image animation. We first transform the image into a coarse video by simple image processing operations such as replication and perspective geometric projections, and then use our general video editor to animate it. As a further application, we can use our method for subject-driven video generation. Extensive qualitative and numerical experiments showcase the remarkable editing ability of our method and establish its superior performance compared to baseline methods.
Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees regarding the generated results, often preventing their use in high-stakes situations. To bridge this gap, we construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way of constructing such intervals is by drawing multiple samples and calculating their bounds. However, this method has several drawbacks: i) slow sampling speeds ii) suboptimal bounds iii) requires training a diffusion model per task. To mitigate these shortcomings we propose Conffusion, wherein we fine-tune a pre-trained diffusion model to predict interval bounds in a single forward pass. We show that Conffusion outperforms the baseline method while being three orders of magnitude faster.
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.
Anomaly detection and segmentation in images has made tremendous progress in recent years while 3D information has often been ignored. The objective of this paper is to further understand the benefit and role of 3D as opposed to color in image anomaly detection. Our study begins by presenting a surprising finding: standard color-only anomaly segmentation methods, when applied to 3D datasets, significantly outperform all current methods. On the other hand, we observe that color-only methods are insufficient for images containing geometric anomalies where shape cannot be unambiguously inferred from 2D. This suggests that better 3D methods are needed. We investigate different representations for 3D anomaly detection and discover that handcrafted orientation-invariant representations are unreasonably effective on this task. We uncover a simple 3D-only method that outperforms all recent approaches while not using deep learning, external pretraining datasets, or color information. As the 3D-only method cannot detect color and texture anomalies, we combine it with 2D color features, granting us the best current results by a large margin (Pixel-wise ROCAUC: 99.2%, PRO: 95.9% on MVTec 3D-AD). We conclude by discussing future challenges for 3D anomaly detection and segmentation.
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.
Image manipulation has attracted much research over the years due to the popularity and commercial importance of the task. In recent years, deep neural network methods have been proposed for many image manipulation tasks. A major issue with deep methods is the need to train on large amounts of data from the same distribution as the target image, whereas collecting datasets encompassing the entire long-tail of images is impossible. In this paper, we demonstrate that simply training a conditional adversarial generator on the single target image is sufficient for performing complex image manipulations. We find that the key for enabling single image training is extensive augmentation of the input image and provide a novel augmentation method. Our network learns to map between a primitive representation of the image (e.g. edges) to the image itself. At manipulation time, our generator allows for making general image changes by modifying the primitive input representation and mapping it through the network. We extensively evaluate our method and find that it provides remarkable performance.