Related papers: RODEO: Replay for Online Object Detection

Multi-Label Online Continual Learning (MOCL) requires models to learn continuously from endless multi-label data streams, facing complex challenges including persistent catastrophic forgetting, potential missing labels, and uncontrollable…

Autonomous robots frequently need to detect "interesting" scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work…

Continual Anomaly Detection (CAD) enables anomaly detection models in learning new classes while preserving knowledge of historical classes. CAD faces two key challenges: catastrophic forgetting and segmentation of small anomalous regions.…

In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This…

Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view consistency objective with an Online Clustering mechanism…

Event-based object detection has recently garnered attention in the computer vision community due to the exceptional properties of event cameras, such as high dynamic range and no motion blur. However, feature asynchronism and sparsity…

Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previous work. This paper presents RDSNet, a novel deep…

Humans learn to recognize and manipulate new objects in lifelong settings without forgetting the previously gained knowledge under non-stationary and sequential conditions. In autonomous systems, the agents also need to mitigate similar…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Although depth extraction with passive sensors has seen remarkable improvement with deep learning, these approaches may fail to obtain correct depth if they are exposed to environments not observed during training. Online adaptation, where…

Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from…

We present an attention-based model for recognizing multiple objects in images. The proposed model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant regions of the input image. We show…

As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding. With the rapid deployment of deep neural networks for SOD tasks, the…

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare,…

We wish to detect specific categories of objects, for online vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a…

Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data…

We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of…

Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from catastrophic forgetting,…

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…