Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept in existing datasets: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) containing 2M pages with all of the associated image, text, and structure data. We verify its utility on three generative tasks: page description generation, section summarization, and contextual image captioning. We design a novel attention mechanism Prefix Global, which selects the most relevant image and text content as global tokens to attend to the rest of the webpage for context. By using page structure to separate such tokens, it performs better than full attention with lower computational complexity. Extensive experiments show that the new data in WikiWeb2M improves task performance compared to prior work.

Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs). Synthetic data from generative models offers a promising direction to mitigate this issue by augmenting underrepresented conditions in the real dataset. However, this introduces another potential source of bias from generative model artifacts in the synthetic data. Indeed, as we will show, prior work uses synthetic data to resolve the model's bias toward $B$, but it doesn't correct the models' bias toward the pair $(B, G)$ where $G$ denotes whether the sample is real or synthetic. Thus, the model could simply learn signals based on the pair $(B, G)$ (\eg, Synthetic Indoors) to make predictions about $Y$ (\eg, Big Dogs). To address this issue, we propose a two-step training pipeline that we call From Fake to Real (FFR). The first step of FFR pre-trains a model on balanced synthetic data to learn robust representations across subgroups. In the second step, FFR fine-tunes the model on real data using ERM or common loss-based bias mitigation methods. By training on real and synthetic data separately, FFR avoids the issue of bias toward signals from the pair $(B, G)$. In other words, synthetic data in the first step provides effective unbiased representations that boosts performance in the second step. Indeed, our analysis of high bias setting (99.9\%) shows that FFR improves performance over the state-of-the-art by 7-14\% over three datasets (CelebA, UTK-Face, and SpuCO Animals).

We propose a self-supervised approach for learning to perform audio source separation in videos based on natural language queries, using only unlabeled video and audio pairs as training data. A key challenge in this task is learning to associate the linguistic description of a sound-emitting object to its visual features and the corresponding components of the audio waveform, all without access to annotations during training. To overcome this challenge, we adapt off-the-shelf vision-language foundation models to provide pseudo-target supervision via two novel loss functions and encourage a stronger alignment between the audio, visual and natural language modalities. During inference, our approach can separate sounds given text, video and audio input, or given text and audio input alone. We demonstrate the effectiveness of our self-supervised approach on three audio-visual separation datasets, including MUSIC, SOLOS and AudioSet, where we outperform state-of-the-art strongly supervised approaches despite not using object detectors or text labels during training.

The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should the label budget (i.e. the amount of money spent on labeling) be allocated among different tasks to achieve optimal multi-task performance? We are the first to propose and formally define the label budget allocation problem in multi-task learning and to empirically show that different budget allocation strategies make a big difference to its performance. We propose a Task-Adaptive Budget Allocation algorithm to robustly generate the optimal budget allocation adaptive to different multi-task learning settings. Specifically, we estimate and then maximize the extent of new information obtained from the allocated budget as a proxy for multi-task learning performance. Experiments on PASCAL VOC and Taskonomy demonstrate the efficacy of our approach over other widely used heuristic labeling strategies.

Multi-source Domain Generalization (DG) measures a classifier's ability to generalize to new distributions of data it was not trained on, given several training domains. While several multi-source DG methods have been proposed, they incur additional complexity during training by using domain labels. Recent work has shown that a well-tuned Empirical Risk Minimization (ERM) training procedure, that is simply minimizing the empirical risk on the source domains, can outperform most existing DG methods. We identify several key candidate techniques to further improve ERM performance, such as better utilization of training data, model parameter selection, and weight-space regularization. We call the resulting method ERM++, and show it significantly improves the performance of DG on five multi-source datasets by over 5% compared to standard ERM, and beats state-of-the-art despite being less computationally expensive. Additionally, we demonstrate the efficacy of ERM++ on the WILDS-FMOW dataset, a challenging DG benchmark. We hope that ERM++ becomes a strong baseline for future DG research. Code is released at https://github.com/piotr-teterwak/erm_plusplus.

Webpages have been a rich resource for language and vision-language tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage 2M (WikiWeb2M) suite; the first to retain the full set of images, text, and structure data available in a page. WikiWeb2M can be used for tasks like page description generation, section summarization, and contextual image captioning.

Recent conditional image generation methods produce images of remarkable diversity, fidelity and realism. However, the majority of these methods allow conditioning only on labels or text prompts, which limits their level of control over the generation result. In this paper, we introduce MaskSketch, an image generation method that allows spatial conditioning of the generation result using a guiding sketch as an extra conditioning signal during sampling. MaskSketch utilizes a pre-trained masked generative transformer, requiring no model training or paired supervision, and works with input sketches of different levels of abstraction. We show that intermediate self-attention maps of a masked generative transformer encode important structural information of the input image, such as scene layout and object shape, and we propose a novel sampling method based on this observation to enable structure-guided generation. Our results show that MaskSketch achieves high image realism and fidelity to the guiding structure. Evaluated on standard benchmark datasets, MaskSketch outperforms state-of-the-art methods for sketch-to-image translation, as well as unpaired image-to-image translation approaches.

Reinforcement Learning (RL) agents trained in simulated environments and then deployed in the real world are often sensitive to the differences in dynamics presented, commonly termed the sim-to-real gap. With the goal of minimizing this gap on resource-constrained embedded systems, we train and live-adapt agents on quadrotors built from off-the-shelf hardware. In achieving this we developed three novel contributions. (i) SwaNNFlight, an open-source firmware enabling wireless data capture and transfer of agents' observations. Fine-tuning agents with new data, and receiving and swapping onboard NN controllers -- all while in flight. We also design SwaNNFlight System (SwaNNFS) allowing new research in training and live-adapting learning agents on similar systems. (ii) Multiplicative value composition, a technique for preserving the importance of each policy optimization criterion, improving training performance and variability in learnt behavior. And (iii) anchor critics to help stabilize the fine-tuning of agents during sim-to-real transfer, online learning from real data while retaining behavior optimized in simulation. We train consistently flight-worthy control policies in simulation and deploy them on real quadrotors. We then achieve live controller adaptation via over-the-air updates of the onboard control policy from a ground station. Our results indicate that live adaptation unlocks a near-50\% reduction in power consumption, attributed to the sim-to-real gap. Finally, we tackle the issues of catastrophic forgetting and controller instability, showing the effectiveness of our novel methods. Project Website: https://github.com/BU-Cyber-Physical-Systems-Lab/SwaNNFS

Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For example, it is hard to study the robustness of these networks to variations of object scale, object pose, scene lighting and 3D occlusions. The main reason is that collecting real datasets with fine-grained naturalistic variations of sufficient scale can be extremely time-consuming and expensive. In this work, we present Counterfactual Simulation Testing, a counterfactual framework that allows us to study the robustness of neural networks with respect to some of these naturalistic variations by building realistic synthetic scenes that allow us to ask counterfactual questions to the models, ultimately providing answers to questions such as "Would your classification still be correct if the object were viewed from the top?" or "Would your classification still be correct if the object were partially occluded by another object?". Our method allows for a fair comparison of the robustness of recently released, state-of-the-art Convolutional Neural Networks and Vision Transformers, with respect to these naturalistic variations. We find evidence that ConvNext is more robust to pose and scale variations than Swin, that ConvNext generalizes better to our simulated domain and that Swin handles partial occlusion better than ConvNext. We also find that robustness for all networks improves with network scale and with data scale and variety. We release the Naturalistic Variation Object Dataset (NVD), a large simulated dataset of 272k images of everyday objects with naturalistic variations such as object pose, scale, viewpoint, lighting and occlusions.

We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students evaluated the two models, on three tasks, at three difficulty levels, across ten prompts each, providing 3,600 ratings. Text-to-image generation has seen rapid progress to the point that many recent models have demonstrated their ability to create realistic high-resolution images for various prompts. However, current text-to-image methods and the broader body of research in vision-language understanding still struggle with intricate text prompts that contain many objects with multiple attributes and relationships. We introduce a new text-to-image benchmark that contains a suite of thirty-two tasks over multiple applications that capture a model's ability to handle different features of a text prompt. For example, asking a model to generate a varying number of the same object to measure its ability to count or providing a text prompt with several objects that each have a different attribute to identify its ability to match objects and attributes correctly. Rather than subjectively evaluating text-to-image results on a set of prompts, our new multi-task benchmark consists of challenge tasks at three difficulty levels (easy, medium, and hard) and human ratings for each generated image.