Related papers: Statistical Context Detection for Deep Lifelong Re…

A common assumption of novelty detection is that the distribution of both "normal" and "novel" data are static. This, however, is often not the case - for example scenarios where data evolves over time or scenarios in which the definition…

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as…

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs…

We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word…

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled…

Deep learning methods have achieved great success in pedestrian detection, owing to its ability to learn features from raw pixels. However, they mainly capture middle-level representations, such as pose of pedestrian, but confuse positive…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a…

Leveraging the characteristics of convolutional layers, neural networks are extremely effective for pattern recognition tasks. However in some cases, their decisions are based on unintended information leading to high performance on…

Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…

A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the…

We address the challenge of sequential data-driven decision-making under context distributional uncertainty. This problem arises in numerous real-world scenarios where the learner optimizes black-box objective functions in the presence of…

Manual labeling of gestures in robot-assisted surgery is labor intensive, prone to errors, and requires expertise or training. We propose a method for automated and explainable generation of gesture transcripts that leverages the abundance…

Online learning policy makes visual trackers more robust against different distortions through learning domain-specific cues. However, the trackers adopting this policy fail to fully leverage the discriminative context of the background…

Active learning is the process of training a model with limited labeled data by selecting a core subset of an unlabeled data pool to label. The large scale of data sets used in deep learning forces most sample selection strategies to employ…

Learning problems in the text processing domain often map the text to a space whose dimensions are the measured features of the text, e.g., its words. Three characteristic properties of this domain are (a) very high dimensionality, (b) both…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretically show that, for good generalization, it is necessary to…