Related papers: When Few-Shot Learning Meets Video Object Detectio…
Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. However, most predicates only occur a handful of times making them difficult to learn. We introduce the first…
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the…
Video object segmentation is challenging yet important in a wide variety of applications for video analysis. Recent works formulate video object segmentation as a prediction task using deep nets to achieve appealing state-of-the-art…
The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training. We introduce a simple pseudo-labelling method to source high-quality…
Transfer learning based approaches have recently achieved promising results on the few-shot detection task. These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal…
Deep neural networks have become the primary learning technique for object recognition. Videos, unlike still images, are temporally coherent which makes the application of deep networks non-trivial. Here, we investigate how motion can aid…
Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data,…
The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…
It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by…
Few-shot learning is a relatively new technique that specializes in problems where we have little amounts of data. The goal of these methods is to classify categories that have not been seen before with just a handful of samples. Recent…
Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on…
Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic…
Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in…
Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that…
Object detection is a fundamental visual recognition problem in computer vision and has been widely studied in the past decades. Visual object detection aims to find objects of certain target classes with precise localization in a given…
The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to…
The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object…
While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific…
We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to…