Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool the network. We present both theoretical and empirical analyses that connect the adversarial robustness of a model to the number of tasks that it is trained on. Experiments on two datasets show that attack difficulty increases as the number of target tasks increase. Moreover, our results suggest that when models are trained on multiple tasks at once, they become more robust to adversarial attacks on individual tasks. While adversarial defense remains an open challenge, our results suggest that deep networks are vulnerable partly because they are trained on too few tasks.
We introduce a video representation learning framework that models the latent goals behind observable human action. Motivated by how children learn to reason about goals and intentions by experiencing failure, we leverage unconstrained video of unintentional action to learn without direct supervision. Our approach models videos as contextual trajectories that represent both low-level motion and high-level action features. Experiments and visualizations show the model is able to predict underlying goals, detect when action switches from intentional to unintentional, and automatically correct unintentional action. Although the model is trained with minimal supervision, it is competitive with highly-supervised baselines, underscoring the role of failure examples for learning goal-oriented video representations. The project website is available at https://aha.cs.columbia.edu/
When we travel, we often encounter new scenarios we have never experienced before, with new sights and new words that describe them. We can use our language-learning ability to quickly learn these new words and correlate them with the visual world. In contrast, language models often do not robustly generalize to novel words and compositions. We propose a framework that learns how to learn text representations from visual context. Experiments show that our approach significantly outperforms the state-of-the-art in visual language modeling for acquiring new words and predicting new compositions. Model ablations and visualizations suggest that the visual modality helps our approach more robustly generalize at these tasks. Project webpage is available at https://expert.cs.columbia.edu/
From just a short glance at a video, we can often tell whether a person's action is intentional or not. Can we train a model to recognize this? We introduce a dataset of in-the-wild videos of unintentional action, as well as a suite of tasks for recognizing, localizing, and anticipating its onset. We train a supervised neural network as a baseline and analyze its performance compared to human consistency on the tasks. We also investigate self-supervised representations that leverage natural signals in our dataset, and show the effectiveness of an approach that uses the intrinsic speed of video to perform competitively with highly-supervised pretraining. However, a significant gap between machine and human performance remains. The project website is available at https://oops.cs.columbia.edu
We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hide behind, and we only give the agents partial observations of their environment using an egocentric perspective. Although we train the model to play this game from scratch, experiments and visualizations suggest that the agent learns to predict its own visibility in the environment. Furthermore, we quantitatively analyze how agent weaknesses, such as slower speed, effect the learned policy. Our results suggest that, although agent weaknesses make the learning problem more challenging, they also cause more useful features to be learned. Our project website is available at: http://www.cs.columbia.edu/ ~bchen/visualhideseek/.
Deep networks are well-known to be fragile to adversarial attacks. Using several standard image datasets and established attack mechanisms, we conduct an empirical analysis of deep representations under attack, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning in order to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also can detect previously unseen adversarial samples. Quantitative experiments show improvement of robustness accuracy by up to 4\% and detection efficiency by up to 6\% according to Area Under Curve (AUC) score over baselines.
This paper focuses on multi-person action forecasting in videos. More precisely, given a history of H previous frames, the goal is to detect actors and to predict their future actions for the next T frames. Our approach jointly models temporal and spatial interactions among different actors by constructing a recurrent graph, using actor proposals obtained with Faster R-CNN as nodes. Our method learns to select a subset of discriminative relations without requiring explicit supervision, thus enabling us to tackle challenging visual data. We refer to our model as Discriminative Relational Recurrent Network (DRRN). Evaluation of action prediction on AVA demonstrates the effectiveness of our proposed method compared to simpler baselines. Furthermore, we significantly improve performance on the task of early action classification on J-HMDB, from the previous SOTA of 48% to 60%.
Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use this model in a number of tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.
We address the problem of phrase grounding by learning a multi-level common semantic space shared by the textual and visual modalities. This common space is instantiated at multiple layers of a Deep Convolutional Neural Network by exploiting its feature maps, as well as contextualized word-level and sentence-level embeddings extracted from a character-based language model. Following a dedicated non-linear mapping for visual features at each level, word, and sentence embeddings, we obtain a common space in which comparisons between the target text and the visual content at any semantic level can be performed simply with cosine similarity. We guide the model by a multi-level multimodal attention mechanism which outputs attended visual features at different semantic levels. The best level is chosen to be compared with text content for maximizing the pertinence scores of image-sentence pairs of the ground truth. Experiments conducted on three publicly available benchmarks show significant performance gains (20%-60% relative) over the state-of-the-art in phrase localization and set a new performance record on those datasets. We also provide a detailed ablation study to show the contribution of each element of our approach.
We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel. Our approach capitalizes on the natural synchronization of the visual and audio modalities to learn models that jointly parse sounds and images, without requiring additional manual supervision. Experimental results on a newly collected MUSIC dataset show that our proposed Mix-and-Separate framework outperforms several baselines on source separation. Qualitative results suggest our model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources.