Related papers: COCO-DR: Combating Distribution Shifts in Zero-Sho…
Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensive training CIR…
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…
Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…
Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always…
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…
We propose a general approach for encouraging fairness in survival analysis models based on minimizing a worst-case error across all subpopulations that occur with at least a user-specified probability. This approach can be used to convert…
Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target domain. For example, high-performing models for…
DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data…
We introduce Coordination-free Collaborative Replication (CCR), a new method for maintaining consistency across replicas in distributed systems without requiring explicit coordination messages. CCR automates conflict resolution, contrasting…
Fine-grained remote sensing datasets often use hierarchical label structures to differentiate objects in a coarse-to-fine manner, with each object annotated across multiple levels. However, embedding this semantic hierarchy into the…
Retrieval augmentation, the practice of retrieving additional data from large auxiliary pools, has emerged as an effective technique for enhancing model performance in the low-data regime. Prior approaches have employed only…
Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and…
Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while…
In zero-shot image retrieval (ZSIR) task, embedding learning becomes more attractive, however, many methods follow the traditional metric learning idea and omit the problems behind zero-shot settings. In this paper, we first emphasize the…
Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…
Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have enabled diverse retrieval methods. However, existing retrieval methods often fail to accurately retrieve results for negation and exclusion…
Dense retrieval has shown great success in passage ranking in English. However, its effectiveness in document retrieval for non-English languages remains unexplored due to the limitation in training resources. In this work, we explore…
Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…
This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…
Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a…