Related papers: Balancing the Causal Effects in Class-Incremental …

Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful.…

A hallmark of life on Earth is the ability of agents to exert causal power and be drivers of subsequent events. This is key to cognition at all scales. Causal emergence, measuring the degree to which an agent exerts unique predictive power…

Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the…

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models must continuously adapt to new data and emerging object categories, but retraining…

In this paper, we introduce audio-visual class-incremental learning, a class-incremental learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual modeling can improve class-incremental learning, but…

Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples. Due to data scarcity, existing FSCIL methods resort to…

In-context reinforcement learning (ICRL) promises fast adaptation to unseen environments without parameter updates, but current methods either cannot improve beyond the training distribution or require near-optimal data, limiting practical…

Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form of multimodal interpretability model. However, existing CBMs…

Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Real-world data streams naturally include the repetition of previous concepts. From a Continual Learning (CL) perspective, repetition is a property of the environment and, unlike replay, cannot be controlled by the agent. Nowadays, the…

In the field of educational assessment, automated scoring systems increasingly rely on deep learning and large language models (LLMs). However, these systems face significant risks of bias amplification, where model prediction gaps between…

Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual information and the…

Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task,…

Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data…

Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT)…

The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task learning is often exacerbated by the scarcity of data for the…

Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation…

In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical deduction, such as mathematical reasoning, remains…

Observational epidemiological studies commonly seek to estimate the causal effect of an exposure on an outcome. Adjustment for potential confounding bias in modern studies is challenging due to the presence of high-dimensional confounding,…