Computer vision publications
-
Modular Adaptation for Cross-Domain Few-Shot Learning
While literature has demonstrated great successes via representation learning, in this work, we show that improvement of downstream tasks can also be achieved by appropriate designs of the adaptation process.
-
Confidence Calibration for Domain Generalization under Covariate Shift
We present novel calibration solutions via domain generalization. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for…
-
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning
We introduce Hybrid Consistency Training to jointly leverage interpolation consistency, including interpolating hidden features, that imposes linear behavior locally and data augmentation consistency that learns robust embeddings against sample variations.
-
RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization
We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud.
-
Lifelong learning using Eigentasks: Task separation, skill acquisition, and selective transfer
We introduce the eigentask framework for lifelong learning. An eigentask is a pairing of a skill that solves a set of related tasks, paired with a generative model that can…
-
Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data.
-
Bit Efficient Quantization for Deep Neural Networks
In this paper, we present a comparison of model-parameter driven quantization approaches that can achieve as low as 3-bit precision without affecting accuracy.
-
Semantically-Aware Attentive Neural Embeddings for 2D Long-Term Visual Localization
We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags.
-
Multi-Sensor Fusion for Motion Estimation in Visually-Degraded Environments
This paper analyzes the feasibility of utilizing multiple low-cost on-board sensors for ground robots or drones navigating in visually-degraded environments.
-
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
We propose novel Stacked Spatio-Temporal Graph Convolutional Networks (Stacked-STGCN) for action segmentation, i.e., predicting and localizing a sequence of actions over long videos.
-
Toward Runtime Throttleable Neural Networks
This paper presents an approach to creating runtime-throttleable NNs that can adaptively balance performance and resource use in response to a control signal.
-
Lucid Explanations Help: Using a Human-AI Image-Guessing Game to Evaluate Machine Explanation Helpfulness
We propose a Twenty-Questions style collaborative image retrieval game as a method of evaluating the efficacy of explanations (visual evidence or textual justification) in the context of Visual Question Answering.