Text-to-image diffusion models produce high quality images but do not offer control over individual instances in the image. We introduce InstanceDiffusion that adds precise instance-level control to text-to-image diffusion models. InstanceDiffusion supports free-form language conditions per instance and allows flexible ways to specify instance locations such as simple single points, scribbles, bounding boxes or intricate instance segmentation masks, and combinations thereof. We propose three major changes to text-to-image models that enable precise instance-level control. Our UniFusion block enables instance-level conditions for text-to-image models, the ScaleU block improves image fidelity, and our Multi-instance Sampler improves generations for multiple instances. InstanceDiffusion significantly surpasses specialized state-of-the-art models for each location condition. Notably, on the COCO dataset, we outperform previous state-of-the-art by 20.4% AP$_{50}^\text{box}$ for box inputs, and 25.4% IoU for mask inputs.
We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training--that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen Video, 90% vs. Nvidia's PYOCO, and 96% vs. Meta's Make-A-Video. Our model outperforms commercial solutions such as RunwayML's Gen2 and Pika Labs. Finally, our factorizing approach naturally lends itself to animating images based on a user's text prompt, where our generations are preferred 96% over prior work.
In this work, we show that text-to-image generative models can be 'inverted' to assess their own text-image understanding capabilities in a completely automated manner. Our method, called SelfEval, uses the generative model to compute the likelihood of real images given text prompts, making the generative model directly applicable to discriminative tasks. Using SelfEval, we repurpose standard datasets created for evaluating multimodal text-image discriminative models to evaluate generative models in a fine-grained manner: assessing their performance on attribute binding, color recognition, counting, shape recognition, spatial understanding. To the best of our knowledge SelfEval is the first automated metric to show a high degree of agreement for measuring text-faithfulness with the gold-standard human evaluations across multiple models and benchmarks. Moreover, SelfEval enables us to evaluate generative models on challenging tasks such as Winoground image-score where they demonstrate competitive performance to discriminative models. We also show severe drawbacks of standard automated metrics such as CLIP-score to measure text faithfulness on benchmarks such as DrawBench, and how SelfEval sidesteps these issues. We hope SelfEval enables easy and reliable automated evaluation for diffusion models.
We tackle the challenging task of unsupervised object localization in this work. Recently, transformers trained with self-supervised learning have been shown to exhibit object localization properties without being trained for this task. In this work, we present Multiple Object localization with Self-supervised Transformers (MOST) that uses features of transformers trained using self-supervised learning to localize multiple objects in real world images. MOST analyzes the similarity maps of the features using box counting; a fractal analysis tool to identify tokens lying on foreground patches. The identified tokens are then clustered together, and tokens of each cluster are used to generate bounding boxes on foreground regions. Unlike recent state-of-the-art object localization methods, MOST can localize multiple objects per image and outperforms SOTA algorithms on several object localization and discovery benchmarks on PASCAL-VOC 07, 12 and COCO20k datasets. Additionally, we show that MOST can be used for self-supervised pre-training of object detectors, and yields consistent improvements on fully, semi-supervised object detection and unsupervised region proposal generation.
Research shows a noticeable drop in performance of object detectors when the training data has missing annotations, i.e. sparsely annotated data. Contemporary methods focus on proxies for missing ground-truth annotations either in the form of pseudo-labels or by re-weighing gradients for unlabeled boxes during training. In this work, we revisit the formulation of sparsely annotated object detection. We observe that sparsely annotated object detection can be considered a semi-supervised object detection problem at a region level. Building on this insight, we propose a region-based semi-supervised algorithm, that automatically identifies regions containing unlabeled foreground objects. Our algorithm then processes the labeled and un-labeled foreground regions differently, a common practice in semi-supervised methods. To evaluate the effectiveness of the proposed approach, we conduct exhaustive experiments on five splits commonly used by sparsely annotated approaches on the PASCAL-VOC and COCO datasets and achieve state-of-the-art performance. In addition to this, we show that our approach achieves competitive performance on standard semi-supervised setups demonstrating the strength and broad applicability of our approach.
In this paper, we introduce a new architecture for few shot learning, the task of teaching a neural network from as few as one or five labeled examples. Inspired by the theoretical results of Alaine et al that Denoising Autoencoders refine features to lie closer to the true data manifold, we present a new training scheme that adds noise at multiple stages of an existing neural architecture while simultaneously learning to be robust to this added noise. This architecture, which we call a Self-Denoising Neural Network (SDNN), can be applied easily to most modern convolutional neural architectures, and can be used as a supplement to many existing few-shot learning techniques. We empirically show that SDNNs out-perform previous state-of-the-art methods for few shot image recognition using the Wide-ResNet architecture on the \textit{mini}ImageNet, tiered-ImageNet, and CIFAR-FS few shot learning datasets. We also perform a series of ablation experiments to empirically justify the construction of the SDNN architecture. Finally, we show that SDNNs even improve few shot performance on the task of human action detection in video using experiments on the ActEV SDL Surprise Activities challenge.
Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate. Thus, boosting is a method for learning an ensemble of classifiers. While boosting has been shown to be very effective for decision trees, its impact on neural networks has not been extensively studied. We prove one important difference between sums of decision trees compared to sums of convolutional neural networks (CNNs) which is that a sum of decision trees cannot be represented by a single decision tree with the same number of parameters while a sum of CNNs can be represented by a single CNN. Next, using standard object recognition datasets, we verify experimentally the well-known result that a boosted ensemble of decision trees usually generalizes much better on testing data than a single decision tree with the same number of parameters. In contrast, using the same datasets and boosting algorithms, our experiments show the opposite to be true when using neural networks (both CNNs and multilayer perceptrons (MLPs)). We find that a single neural network usually generalizes better than a boosted ensemble of smaller neural networks with the same total number of parameters.
We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset. While existing methods show results on datasets with less cluttered scenes and fewer object instances per image, we present our results on the challenging COCO dataset. Moreover, we argue that, rather than discovering new categories from scratch, discovery algorithms can benefit from identifying what is already known and focusing their attention on the unknown. We propose a method to use prior knowledge about certain object categories to discover new categories by leveraging two memory modules, namely Working and Semantic memory. We show the performance of our detector on the COCO minival dataset to demonstrate its in-the-wild capabilities.
The relative spatial layout of a human and an object is an important cue for determining how they interact. However, until now, spatial layout has been used just as side-information for detecting human-object interactions (HOIs). In this paper, we present a method for exploiting this spatial layout information for detecting HOIs in images. The proposed method consists of a layout module which primes a visual module to predict the type of interaction between a human and an object. The visual and layout modules share information through lateral connections at several stages. The model uses predictions from the layout module as a prior to the visual module and the prediction from the visual module is given as the final output. It also incorporates semantic information about the object using word2vec vectors. The proposed model reaches an mAP of 24.79% for HICO-Det dataset which is about 2.8% absolute points higher than the current state-of-the-art.