Related papers: RODEO: Replay for Online Object Detection

The aim of this research is to detect small objects with low resolution and noise. The existing real time object detection algorithm is based on the deep neural network of convolution need to perform multilevel convolution and pooling…

Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or constantly changing ones…

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2)…

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual…

The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

For humans, object detection, recognition, and tracking are innate. These provide the ability for human to perceive their environment and objects within their environment. This ability however doesn't translate well in computers. In…

The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…

Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced…

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize…

Can we see it all? Do we know it All? These are questions thrown to human beings in our contemporary society to evaluate our tendency to solve problems. Recent studies have explored several models in object detection; however, most have…

Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address…

Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may…

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…

The field of object detection has made significant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet…

Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition…

Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets. Their main drawback however is that these methods are hardly able to recognize visual…

We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic…