Related papers: DETRs with Collaborative Hybrid Assignments Traini…

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks, as well as for efficient scaling to large compute clusters. As current approaches suffer from limited bandwidth…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

Most approaches to dense anomaly detection rely on generative modeling or on discriminative methods that train with negative data. We consider a recent hybrid method that optimizes the same shared representation according to cross-entropy…

Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item…

Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped pedestrians. The recently proposed end-to-end…

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…

This paper describes our system to SemEval-2026 Task 3 Track A Subtask 1 on Dimensional Aspect Sentiment Regression (DimASR). We propose a lightweight and resource-efficient system built entirely on multilingual pre-trained encoders,…

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

Although deep learning-based methods have achieved excellent performance on SAR ATR, the fact that it is difficult to acquire and label a lot of SAR images makes these methods, which originally performed well, perform weakly. This may be…

Federated Learning offers a way to train deep neural networks in a distributed fashion. While this addresses limitations related to distributed data, it incurs a communication overhead as the model parameters or gradients need to be…

The integration of Artificial Intelligence into the modern educational system is rapidly evolving, particularly in monitoring student behavior in classrooms, a task traditionally dependent on manual observation. This conventional method is…

The information retrieval community has made significant progress in improving the efficiency of Dual Encoder (DE) dense passage retrieval systems, making them suitable for latency-sensitive settings. However, many proposed procedures are…

While large language models are primarily used on natural language tasks, they have also shown great promise when adapted to new modalities, e.g., for scientific machine learning tasks. Most proposed approaches for such cross-modal…

Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available…

Learning unified text embeddings that excel across diverse downstream tasks is a central goal in representation learning, yet negative transfer remains a persistent obstacle. This challenge is particularly pronounced when jointly training a…

The acquisition of high-quality labeled synthetic aperture radar (SAR) data is challenging due to the demanding requirement for expert knowledge. Consequently, the presence of unreliable noisy labels is unavoidable, which results in…

The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate…

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach,…

Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of encodings on centralized training data. However, in many…