Related papers: nVFNet-RDC: Replay and Non-Local Distillation Coll…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Object detection is a crucial task in computer vision that aims to identify and localize objects in images or videos. The recent advancements in deep learning and Convolutional Neural Networks (CNNs) have significantly improved the…

As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large teacher models to…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to correctly recognize previously learned classes of objects when…

Object detection has achieved remarkable accuracy through deep learning, yet these improvements often come with increased computational cost, limiting deployment on resource-constrained devices. Knowledge Distillation (KD) provides an…

In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors. We observe that off-the-shelf KD methods manifest their efficacy only when the teacher model and student counterpart share similar intermediate…

In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved…

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…

Knowledge distillation(KD) is a widely-used technique to train compact models in object detection. However, there is still a lack of study on how to distill between heterogeneous detectors. In this paper, we empirically find that better FPN…

Object detection has achieved promising performance on clean datasets, but how to achieve better tradeoff between the adversarial robustness and clean precision is still under-explored. Adversarial training is the mainstream method to…

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our…

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely studied, most assume stationary data distributions - an…

Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past knowledge in a shared single-model framework with low storage…

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for…

Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel…