Related papers: RICO: Two Realistic Benchmarks and an In-Depth Ana…
Data in real-world object detection often exhibits the long-tailed distribution. Existing solutions tackle this problem by mitigating the competition between the head and tail categories. However, due to the scarcity of training samples,…
The rapid progress in machine learning models has significantly boosted the potential for real-world applications such as autonomous vehicles, disease diagnoses, and recognition of emergencies. The performance of many machine learning…
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…
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…
Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…
Real-world environments are inherently non-stationary, frequently introducing new classes over time. This is especially common in time series classification, such as the emergence of new disease classification in healthcare or the addition…
While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is well known that, in…
Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited…
While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments, their success in everyday tasks like visual navigation has been limited, particularly under significant…
This work proposes an incremental learning (IL) framework for wearable sensor human activity recognition (HAR) that tackles two challenges simultaneously: catastrophic forgetting and non-uniform inputs. The scalable framework, iKAN,…
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated…
Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied agents. However, many existing locomotion benchmarks primarily focus on simplified toy tasks, often failing to capture the complexity of real-world…
Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments, requiring models to adjust to evolving domains while preserving historical knowledge. DIL faces two critical challenges in the context of…
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…
With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three…
The Image Difference Captioning (IDC) task aims to describe the visual differences between two similar images with natural language. The major challenges of this task lie in two aspects: 1) fine-grained visual differences that require…
Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed…
Imitation Learning (IL) is an effective learning paradigm exploiting the interactions between agents and environments. It does not require explicit reward signals and instead tries to recover desired policies using expert demonstrations. In…
Large-scale models trained on extensive datasets have become the standard due to their strong generalizability across diverse tasks. In-context learning (ICL), widely used in natural language processing, leverages these models by providing…