相关论文: SCISSOR: Mitigating Semantic Bias through Cluster-…

Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned…

Deep learning models can excel on medical tasks, yet often experience spurious correlations, known as shortcut learning, leading to poor generalization in new environments. Particularly in medical imaging, where multiple spurious…

Point cloud semantic segmentation can significantly enhance the perception of an intelligent agent. Nevertheless, the discriminative capability of the segmentation network is influenced by the quantity of samples available for different…

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Change detection is a key task in Earth observation applications. Recently, deep learning methods have demonstrated strong performance and widespread application. However, change detection faces data scarcity due to the labor-intensive…

Synapse crossbar is an elementary structure in Neuromorphic Computing Systems (NCS). However, the limited size of crossbars and heavy routing congestion impedes the NCS implementations of big neural networks. In this paper, we propose a…

Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. To alleviate this, we propose a framework to exploit intermediate self-supervisions in each stage of deep nets, called the…

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…

Recent advances in reinforcement learning from human feedback (RLHF) and preference optimization have substantially improved the usability, coherence, and safety of large language models. However, recurring behaviors such as performative…

Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data. Prior works on causal learning assume that the high-level…

Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging…

Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the…

Multi-Instance Learning (MIL) is pivotal for analyzing complex, weakly labeled datasets, such as whole-slide images (WSIs) in computational pathology, where bags comprise unordered collections of instances with sparse diagnostic relevance.…

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is…

Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases,…

Several prior studies have suggested that word frequency biases can cause the Bert model to learn indistinguishable sentence embeddings. Contrastive learning schemes such as SimCSE and ConSERT have already been adopted successfully in…

Semantic communications (SCs) play a central role in shaping the future of the sixth generation (6G) wireless systems, which leverage rapid advances in deep learning (DL). In this regard, end-to-end optimized DL-based joint source-channel…

Deep learning has revolutionized medical image segmentation, yet its full potential remains constrained by the paucity of annotated datasets. While diffusion models have emerged as a promising approach for generating synthetic image-mask…

Ranking samples by fine-grained estimates of spuriosity (the degree to which spurious cues are present) has recently been shown to significantly benefit bias mitigation, over the traditional binary biased-\textit{vs}-unbiased partitioning…