Weakly-supervised action localization problem requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multiple Instance Learning (MIL) framework, where a bag (video) contains multiple instances (action segments). Since only the bag's label is known, the main challenge is to assign which key instances within the bag trigger the bag's label. Most previous models use an attention-based approach. These models use attention to generate the bag's representation from instances and then train it via bag's classification. In this work, we explicitly model the key instances assignment as a hidden variable and adopt an Expectation-Maximization framework. We derive two pseudo-label generation schemes to model the E and M process and iteratively optimize the likelihood lower bound. We also show that previous attention-based models implicitly violate the MIL assumptions that instances in negative bags should be uniformly negative. In comparison, Our EM-MIL approach more accurately models these assumptions. Our model achieves state-of-the-art performance on two standard benchmarks, THUMOS14 and ActivityNet1.2, and shows the superiority of detecting relative complete action boundary in videos containing multiple actions.
Many interesting events in the real world are rare making preannotated machine learning ready videos a rarity in consequence. Thus, temporal activity detection models that are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection based on proposal regression which detects the start and end time of the activities in untrimmed videos. Our model is end-to-end trainable, takes into account the frame rate differences between few-shot activities and untrimmed test videos, and can benefit from additional few-shot examples. We experiment on three large scale benchmarks for temporal activity detection (ActivityNet1.2, ActivityNet1.3 and THUMOS14 datasets) in a few-shot setting. We also study the effect on performance of different amount of overlap with activities used to pretrain the video classification backbone and propose corrective measures for future works in this domain. Our code will be made available.
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We show that shared features are significantly less prone to forgetting and propose a novel hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks. Our model combines architecture growth to prevent forgetting of task-specific skills and an experience replay approach to preserve shared skills. We demonstrate our hybrid approach is effective in avoiding forgetting and show it is superior to both architecture-based and memory-based approaches on class incrementally learning of a single dataset as well as a sequence of multiple datasets in image classification. Our code is available at \url{https://github.com/facebookresearch/Adversarial-Continual-Learning}.
Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.
In supervised learning, smoothing label/prediction distribution in neural network training has been proven useful in preventing the model from being over-confident, and is crucial for learning more robust visual representations. This observation motivates us to explore the way to make predictions flattened in unsupervised learning. Considering that human annotated labels are not adopted in unsupervised learning, we introduce a straightforward approach to perturb input image space in order to soften the output prediction space indirectly. Despite its conceptual simplicity, we show empirically that with the simple solution -- image mixture, we can learn more robust visual representations from the transformed input, and the benefits of representations learned from this space can be inherited by the linear classification and downstream tasks.
Meta-learning has become a popular framework for few-shot learning in recent years, with the goal of learning a model from collections of few-shot classification tasks. While more and more novel meta-learning models are being proposed, our research has uncovered simple baselines that have been overlooked. We present a Meta-Baseline method, by pre-training a classifier on all base classes and meta-learning on a nearest-centroid based few-shot classification algorithm, it outperforms recent state-of-the-art methods by a large margin. Why does this simple method work so well? In the meta-learning stage, we observe that a model generalizing better on unseen tasks from base classes can have a decreasing performance on tasks from novel classes, indicating a potential objective discrepancy. We find both pre-training and inheriting a good few-shot classification metric from the pre-trained classifier are important for Meta-Baseline, which potentially helps the model better utilize the pre-trained representations with stronger transferability. Furthermore, we investigate when we need meta-learning in this Meta-Baseline. Our work sets up a new solid benchmark for this field and sheds light on further understanding the phenomenons in the meta-learning framework for few-shot learning.
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data-efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.
Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task, but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category.
Generating realistic images of complex visual scenes becomes very challenging when one wishes to control the structure of the generated images. Previous approaches showed that scenes with few entities can be controlled using scene graphs, but this approach struggles as the complexity of the graph (number of objects and edges) increases. Moreover, current approaches fail to generalize conditioned on the number of objects or when given different input graphs which are semantic equivalent. In this work, we propose a novel approach to mitigate these issues. We present a novel model which can inherently learn canonical graph representations, thus ensuring that semantically similar scene graphs will result in similar predictions. In addition, the proposed model can better capture object representation independently of the number of objects in the graph. We show improved performance of the model on three different benchmarks: Visual Genome, COCO and CLEVR.
Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the scene. Recent work has explored the TextVQA task that requires reading and understanding text in images to answer a question. However, existing approaches for TextVQA are mostly based on custom pairwise fusion mechanisms between a pair of two modalities and are restricted to a single prediction step by casting TextVQA as a classification task. In this work, we propose a novel model for the TextVQA task based on a multimodal transformer architecture accompanied by a rich representation for text in images. Our model naturally fuses different modalities homogeneously by embedding them into a common semantic space where self-attention is applied to model inter- and intra- modality context. Furthermore, it enables iterative answer decoding with a dynamic pointer network, allowing the model to form an answer through multi-step prediction instead of one-step classification. Our model outperforms existing approaches on three benchmark datasets for the TextVQA task by a large margin.