Gao Huang

TL;DR: In this article, the authors propose an end-to-end learned approach for disparity prediction in the anytime setting, during which the model can be queried at any time to output its current best estimate.

TL;DR: In this paper, a novel Resolution Adaptive Network (RANet) is proposed to reduce the spatial redundancy involved in inferring high-resolution inputs by first routing the input images to a lightweight sub-network that efficiently extracts low-resolution representations, and those samples with high prediction confidence will exit early from the network without being further processed.

TL;DR: This work proposes a novel approach for disparity prediction in the anytime setting that can trade off computation and accuracy at inference time, and can process $1242 \times 375$ resolution images within a range of 10-35 FPS on an NVIDIA Jetson TX2 module with only marginal increases in error.

TL;DR: This work proposes a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning, which consistently improves the computational efficiency of a wide variety of deep models.

TL;DR: This paper focuses on spatial redundancy of input samples and proposes a novel Resolution Adaptive Network (RANet), inspired by the intuition that low-resolution representations are sufficient for classifying “easy” inputs containing large objects with prototypical features, while only some “hard” samples need spatially detailed information.