相关论文: TRACER: Persistent Regularization for Robust Multi…

Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new…

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger…

Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing…

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic…

Given the real-time demands of UAV tracking, many methods simplify the backbone to reduce computation, but this often weakens feature representation and degrades performance in complex scenarios. To alleviate this issue, we propose EATrack,…

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network…

The balance between stability and plasticity remains a fundamental challenge in pretrained model-based incremental object detection (PTMIOD). While existing PTMIOD methods demonstrate strong performance on in-domain tasks aligned with…

Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…

Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging…

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Underpinning the success of deep learning is effective regularizations that allow a variety of priors in data to be modeled. For example, robustness to adversarial perturbations, and correlations between multiple modalities. However, most…

Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional neural networks (CNNs) against commonly occurring distortions…

Apples growing in natural environments often face severe visual obstructions from leaves and branches. This significantly increases the risk of false detections in object detection tasks, thereby escalating the challenge. Addressing this…

Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference…

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

Existing unsupervised distillation-based methods rely on the differences between encoded and decoded features to locate abnormal regions in test images. However, the decoder trained only on normal samples still reconstructs abnormal patch…

Despite commendable achievements made by existing work, prevailing multimodal sarcasm detection studies rely more on textual content over visual information. It unavoidably induces spurious correlations between textual words and labels,…

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially…

Knowledge distillation (KD) aims to transfer knowledge from a large-scale teacher model to a lightweight one, significantly reducing computational and storage requirements. However, the inherent learning capacity gap between the teacher and…