As machine learning is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable. Despite the recent growth of interpretability work, there is a lack of systematic evaluation of proposed techniques. In this work, we propose a novel human evaluation framework HIVE (Human Interpretability of Visual Explanations) for diverse interpretability methods in computer vision; to the best of our knowledge, this is the first work of its kind. We argue that human studies should be the gold standard in properly evaluating how interpretable a method is to human users. While human studies are often avoided due to challenges associated with cost, study design, and cross-method comparison, we describe how our framework mitigates these issues and conduct IRB-approved studies of four methods that represent the diversity of interpretability works: GradCAM, BagNet, ProtoPNet, and ProtoTree. Our results suggest that explanations (regardless of if they are actually correct) engender human trust, yet are not distinct enough for users to distinguish between correct and incorrect predictions. Lastly, we also open-source our framework to enable future studies and to encourage more human-centered approaches to interpretability.
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years. In this paper, we focus on the less-studied setting of multi-query video retrieval, where multiple queries are provided to the model for searching over the video archive. We first show that the multi-query retrieval task is more pragmatic and representative of real-world use cases and better evaluates retrieval capabilities of current models, thereby deserving of further investigation alongside the more prevalent single-query retrieval setup. We then propose several new methods for leveraging multiple queries at training time to improve over simply combining similarity outputs of multiple queries from regular single-query trained models. Our models consistently outperform several competitive baselines over three different datasets. For instance, Recall@1 can be improved by 4.7 points on MSR-VTT, 4.1 points on MSVD and 11.7 points on VATEX over a strong baseline built on the state-of-the-art CLIP4Clip model. We believe further modeling efforts will bring new insights to this direction and spark new systems that perform better in real-world video retrieval applications. Code is available at https://github.com/princetonvisualai/MQVR.
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in undesirable ways. In this work, we study bias propagation pathways within image captioning, focusing specifically on the COCO dataset. Prior work has analyzed gender bias in captions using automatically-derived gender labels; here we examine racial and intersectional biases using manual annotations. Our first contribution is in annotating the perceived gender and skin color of 28,315 of the depicted people after obtaining IRB approval. Using these annotations, we compare racial biases present in both manual and automatically-generated image captions. We demonstrate differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people. Further, we find the magnitude of these differences to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Code and data is available at https://princetonvisualai.github.io/imagecaptioning-bias .
Singh et al. (2020) point out the dangers of contextual bias in visual recognition datasets. They propose two methods, CAM-based and feature-split, that better recognize an object or attribute in the absence of its typical context while maintaining competitive within-context accuracy. To verify their performance, we attempted to reproduce all 12 tables in the original paper, including those in the appendix. We also conducted additional experiments to better understand the proposed methods, including increasing the regularization in CAM-based and removing the weighted loss in feature-split. As the original code was not made available, we implemented the entire pipeline from scratch in PyTorch 1.7.0. Our implementation is based on the paper and email exchanges with the authors. We found that both proposed methods in the original paper help mitigate contextual bias, although for some methods, we could not completely replicate the quantitative results in the paper even after completing an extensive hyperparameter search. For example, on COCO-Stuff, DeepFashion, and UnRel, our feature-split model achieved an increase in accuracy on out-of-context images over the standard baseline, whereas on AwA, we saw a drop in performance. For the proposed CAM-based method, we were able to reproduce the original paper's results to within 0.5$\%$ mAP. Our implementation can be found at https://github.com/princetonvisualai/ContextualBias.
Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy protection; nevertheless, object recognition research typically assumes access to complete, unobfuscated images. In this paper, we explore the effects of face obfuscation on the popular ImageNet challenge visual recognition benchmark. Most categories in the ImageNet challenge are not people categories; however, many incidental people appear in the images, and their privacy is a concern. We first annotate faces in the dataset. Then we demonstrate that face blurring -- a typical obfuscation technique -- has minimal impact on the accuracy of recognition models. Concretely, we benchmark multiple deep neural networks on face-blurred images and observe that the overall recognition accuracy drops only slightly (no more than 0.68%). Further, we experiment with transfer learning to 4 downstream tasks (object recognition, scene recognition, face attribute classification, and object detection) and show that features learned on face-blurred images are equally transferable. Our work demonstrates the feasibility of privacy-aware visual recognition, improves the highly-used ImageNet challenge benchmark, and suggests an important path for future visual datasets. Data and code are available at https://github.com/princetonvisualai/imagenet-face-obfuscation.
Mitigating bias in machine learning systems requires refining our understanding of bias propagation pathways: from societal structures to large-scale data to trained models to impact on society. In this work, we focus on one aspect of the problem, namely bias amplification: the tendency of models to amplify the biases present in the data they are trained on. A metric for measuring bias amplification was introduced in the seminal work by Zhao et al. (2017); however, as we demonstrate, this metric suffers from a number of shortcomings including conflating different types of bias amplification and failing to account for varying base rates of protected classes. We introduce and analyze a new, decoupled metric for measuring bias amplification, $\text{BiasAmp}_{\rightarrow}$ (Directional Bias Amplification). We thoroughly analyze and discuss both the technical assumptions and the normative implications of this metric. We provide suggestions about its measurement by cautioning against predicting sensitive attributes, encouraging the use of confidence intervals due to fluctuations in the fairness of models across runs, and discussing the limitations of what this metric captures. Throughout this paper, we work to provide an interrogative look at the technical measurement of bias amplification, guided by our normative ideas of what we want it to encompass.
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes (e.g., gender, race) are known to learn and exploit those correlations. In this work, we introduce a method for training accurate target classifiers while mitigating biases that stem from these correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We augment the original dataset with this perturbed generated data, and empirically demonstrate that target classifiers trained on the augmented dataset exhibit a number of both quantitative and qualitative benefits. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space.