相关论文: Refined Response Distillation for Class-Incrementa…

Traditional object detection are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. Knowledge distillation is a straightforward…

Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to…

Incremental object detection (IOD) aims to continuously expand the capability of a model to detect novel categories while preserving its performance on previously learned ones. When adopting a transformer-based detection model to perform…

The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for incremental…

Existing Incremental Object Detection (IOD) methods partially alleviate catastrophic forgetting when incrementally detecting new objects in real-world scenarios. However, many of these methods rely on the assumption that unlabeled old-class…

The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…

Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…

We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A na\"ive approach to incremental object counting would suffer from…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model…

Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically,…

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Recent advances in object detection have benefited significantly from rapid developments in deep neural networks. However, neural networks suffer from the well-known issue of catastrophic forgetting, which makes continual or lifelong…

Decision transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static datasets and inherent architectural limitations.…

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…

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…

We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…

Question answering (QA) models are well-known to exploit data bias, e.g., the language prior in visual QA and the position bias in reading comprehension. Recent debiasing methods achieve good out-of-distribution (OOD) generalizability with…

Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods…