HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
arXiv:2605.06157 · doi:10.18653/v1/2023.conll-1.24
Abstract
Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image-text pairs, models fail to show a fine-grained understanding of the combined semantics of these modalities. To address this issue we propose Hard Negative Captions (HNC): an automatically created dataset containing foiled hard negative captions for ITM training towards achieving fine-grained cross-modal comprehension in VL. Additionally, we provide a challenging manually-created test set for benchmarking models on a fine-grained cross-modal mismatch task with varying levels of compositional complexity. Our results show the effectiveness of training on HNC by improving the models' zero-shot capabilities in detecting mismatches on diagnostic tasks and performing robustly under noisy visual input scenarios. Also, we demonstrate that HNC models yield a comparable or better initialization for fine-tuning
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Decoupled Weight Decay Regularization
- On the difficulty of training Recurrent Neural Networks
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations
- VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
- A Comprehensive Survey of Scene Graphs: Generation and Application
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning
- VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
- Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions