Hexiang Hu is a Computer Science Ph.D. student in Viterbi School of Engineering at University of Southern California (USC), working with Prof. Fei Sha. Prior to this, He was a Ph.D. student in Henry Samueli School of Engineering and Applied Science at University of California, Los Angeles (UCLA). He earned his Bachelor’s degrees in Computer Science from Zhejiang University and Simon Fraser University with honor. He worked with Prof. Greg Mori during his undergrads. His research interests include Machine Learning, Computer Vision and Natural Language Processing. [ Résumé ]
In this paper, we propose learning representations from a set of implied, visually grounded expressions between image and text, automatically mined from those datasets. In particular, we use denotation graphs to represent how specific concepts (such as sentences describing images) can be linked to abstract and generic concepts (such as short phrases) that are also visually grounded. We propose methods to incorporate such relations into learning representation.
In this paper, we investigate the problem of generalized few-shot learning (GFSL) -- a model during the deployment is required to not only learn about 'tail' categories with few shots but simultaneously classify the 'head' and 'tail' categories. We propose the ClAssifier SynThesis LEarning (CASTLE), a learning framework that learns how to synthesize calibrated few-shot classifiers in addition to the multi-class classifiers of 'head' classes with a shared neural dictionary, shedding light upon the inductive GFSL.
In this paper, we study how an agent can navigate long paths when learning from a corpus that consists of shorter ones .We show that existing state-of-the-art agents do not generalize well. To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially.
In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and discriminative. We empirically investigated various set-to-set functions and observed Transformer is most effective, as it naturally satisfies the key properties.
One important limitation of MAML is that they seek a common initialization shared across tasks, which made it suffering from adapting tasks of a multimodal distribution. This paper propose a generic method that augment MAML with the capability of identifying the task mode using a model based learner, such that it can adapt quickly with a few gradient updates.
This paper presents an alternative evaluation task for visual-grounding systems: given a caption the system is asked to select the image that best matches the caption from a pair of semantically similar images. The system's accuracy on this Binary Image SelectiON (BISON) task is not only interpretable, but also measures the ability to relate fine-grained text content in the caption to visual content in the images.
We define a new task, Personality-Captions, where the goal is to be as engaging to humans as possible by incorporating controllable style and personality traits. We collect and release a large dataset of 201,858 of such captions conditioned over 215 possible traits.
In this paper, we consider the problem of learning to simultaneously transfer across both environments (ENV) and tasks (TASK), probably more importantly, by learning from only sparse (ENV, TASK) pairs out of all possible combinations. We propose a compositional neural network which depicts a meta rule for composing policies from the environment and task embeddings.
We propose a generic structured model that leverages diverse label relations to improve image classification performance. It employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. The design of this framework naurally extends to leverage partial observations in the label space to inference the rest label space.
We show the design of the decoy answers has a significant impact on how and what the learning models learn from the datasets. In particular, the resulting learner can ignore the visual information, the question, or the both while still doing well on the task.
We propose a novel probabilistic model for visual question answering.