More Like this

1. CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision

   Shrivastava, Aman; Selvaraju, Ramprasaath R.; Naik, Nikhil; Ordonez, Vicente (January 2023, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics)

   Ruiz, Francisco; Dy, Jennifer; van de Meent, Jan-Willem (Ed.)

   We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimization of its contrastive learning objective. We accomplish this by taking advantage of an information efficient lower-bound to maximize the mutual information between the two input modalities. This allows CLIP-Lite to be trained with significantly reduced amounts of data and batch sizes while obtaining better performance than CLIP at the same scale. We evaluate CLIP-Lite by pretraining on the COCO-Captions dataset and testing transfer learning to other datasets. CLIP-Lite obtains a +14.0 mAP absolute gain in performance on Pascal VOC classification, and a +22.1 top-1 accuracy gain on ImageNet, while being comparable or superior to other, more complex, text-supervised models. CLIP-Lite is also superior to CLIP on image and text retrieval, zero-shot classification, and visual grounding. Finally, we show that CLIP-Lite can leverage language semantics to encourage bias-free visual representations that can be used in downstream tasks. Implementation: https://github.com/4m4n5/CLIP-Lite 

   more » « less
2. Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models

   Zhiqiu Lin, Samuel Yu (June 2023, CVPR)

   The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples may not be sufficient to characterize an entire concept class. In contrast, humans use cross-modal information to learn new concepts efficiently. In this work, we demonstrate that one can indeed build a better visual dog classifier by reading about dogs and listening to them bark. To do so, we exploit the fact that recent multimodal foundation models such as CLIP are inherently cross-modal, mapping different modalities to the same representation space. Specifically, we propose a simple cross-modal adaptation approach that learns from few-shot examples spanning different modalities. By repurposing class names as additional one-shot training samples, we achieve SOTA results with an embarrassingly simple linear classifier for vision-language adaptation. Furthermore, we show that our approach can benefit existing methods such as prefix tuning, adapters, and classifier ensembling. Finally, to explore other modalities beyond vision and language, we construct the first (to our knowledge) audiovisual few-shot benchmark and use cross-modal training to improve the performance of both image and audio classification. 

   more » « less
3. Multi-Modal Contrastive Learning for Proteins by Combining Domain-Informed Views

   Xu, Haotian; You, Yuning; Shen, Yang (March 2024, Machine Learning for Genomics Explorations workshop at ICLR 2024)

   Proteins, often represented as multi-modal data of 1D sequences and 2D/3D structures, provide a motivating example for the communities of machine learning and computational biology to advance multi-modal representation learning. Protein language models over sequences and geometric deep learning over structures learn excellent single-modality representations for downstream tasks. It is thus desirable to fuse the single-modality models for better representation learning, but it remains an open question on how to fuse them effectively into multi-modal representation learning with a modest computational cost yet significant downstream performance gain. To answer the question, we propose to make use of separately pretrained single-modality models, integrate them in parallel connections, and continuously pretrain them end-to-end under the framework of multimodal contrastive learning. The technical challenge is to construct views for both intra- and inter-modality contrasts while addressing the heterogeneity of various modalities, particularly various levels of semantic robustness. We address the challenge by using domain knowledge of protein homology to inform the design of positive views, specifically protein classifications of families (based on similarities in sequences) and superfamilies (based on similarities in structures). We also assess the use of such views compared to, together with, and composed to other positive views such as identity and cropping. Extensive experiments on enzyme classification and protein function prediction benchmarks demonstrate the potential of domain-informed view construction and combination in multi-modal contrastive learning 

   more » « less
4. Learning Factorized Multimodal Representations

   Tsai, Yao-Hung Hubert; Liang, Paul Pu; Zadeh, Amir; Morency, Louis-Philippe; Salakhutdinov, Ruslan (February 2019, International Conference on Representation Learning)

   Learning multimodal representations is a fundamentally complex research problem due to the presence of multiple heterogeneous sources of information. Although the presence of multiple modalities provides additional valuable information, there are two key challenges to address when learning from multimodal data: 1) models must learn the complex intra-modal and cross-modal interactions for prediction and 2) models must be robust to unexpected missing or noisy modalities during testing. In this paper, we propose to optimize for a joint generative-discriminative objective across multimodal data and labels. We introduce a model that factorizes representations into two sets of independent factors: multimodal discriminative and modality-specific generative factors. Multimodal discriminative factors are shared across all modalities and contain joint multimodal features required for discriminative tasks such as sentiment prediction. Modality-specific generative factors are unique for each modality and contain the information required for generating data. Experimental results show that our model is able to learn meaningful multimodal representations that achieve state-of-the-art or competitive performance on six multimodal datasets. Our model demonstrates flexible generative capabilities by conditioning on independent factors and can reconstruct missing modalities without significantly impacting performance. Lastly, we interpret our factorized representations to understand the interactions that influence multimodal learning. 

   more » « less
5. A text-guided protein design framework

   https://doi.org/10.1038/s42256-025-01011-z  

   Liu, Shengchao; Li, Yanjing; Li, Zhuoxinran; Gitter, Anthony; Zhu, Yutao; Lu, Jiarui; Xu, Zhao; Nie, Weili; Ramanathan, Arvind; Xiao, Chaowei; et al (March 2025, Nature Machine Intelligence)

   Current AI-assisted protein design utilizes mainly protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in text format describing proteins’ high-level functionalities, yet whether the incorporation of such text data can help in protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multimodal framework that leverages textual descriptions for protein design. ProteinDT consists of three consecutive steps: ProteinCLAP, which aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality and a decoder that creates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441,000 text and protein pairs. We quantitatively verify the effectiveness of ProteinDT on three challenging tasks: (1) over 90% accuracy for text-guided protein generation; (2) best hit ratio on 12 zero-shot text-guided protein editing tasks; (3) superior performance on four out of six protein property prediction benchmarks. 

   more » « less