Related papers: WarpNet: Weakly Supervised Matching for Single-vie…
Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision. The successes of multiple instance learning in this task for natural…
In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations…
One-shot image classification aims to train image classifiers over the dataset with only one image per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images per class. In this…
Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to…
Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require…
We consider the problem of two-view matching under significant viewpoint changes with view synthesis. We propose two novel methods, minimizing the view synthesis overhead. The first one, named DenseAffNet, uses dense affine shapes estimates…
Accurate automatic medical image segmentation relies on high-quality, dense annotations, which are costly and time-consuming. Weakly supervised learning provides a more efficient alternative by leveraging sparse and coarse annotations…
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as supervision signals, and struggle to make the localization…
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth…
Most of the previous methods for table recognition rely on training datasets containing many richly annotated table images. Detailed table image annotation, e.g., cell or text bounding box annotation, however, is costly and often…
In recent years, learning-based image registration methods have gradually moved away from direct supervision with target warps to instead use self-supervision, with excellent results in several registration benchmarks. These approaches…
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper…
Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…
The weakly supervised sound event detection problem is the task of predicting the presence of sound events and their corresponding starting and ending points in a weakly labeled dataset. A weak dataset associates each training sample (a…
Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning.…
The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. However, recent work has challenged this…
Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…
Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount…
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This…
This paper proposes a weakly- and self-supervised deep convolutional neural network (WSSDCNN) for content-aware image retargeting. Our network takes a source image and a target aspect ratio, and then directly outputs a retargeted image.…