Related papers: Continual Object Detection via Prototypical Task C…

Current gait recognition methodologies generally necessitate retraining when encountering new datasets. Nevertheless, retrained models frequently encounter difficulties in preserving knowledge from previous datasets, leading to a…

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…

Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective may inadvertently compromise the performance of another. A…

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training…

The major approaches of transfer learning in computer vision have tried to adapt the source domain to the target domain one-to-one. However, this scenario is difficult to apply to real applications such as video surveillance systems. As…

We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to…

Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.…

Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive generative recommender model (GRM) performs prediction based on…

The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much…

Deep learning has recently achieved remarkable performance in image classification tasks, which depends heavily on massive annotation. However, the classification mechanism of existing deep learning models seems to contrast to humans'…

Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in…

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized…

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images. Despite that many methods proposed recently have achieved remarkable performance, most of them directly…

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique…