Papers › Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning

Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning

7 Apr 2021CVPR 2021 1arXiv:2104.03135archive 2025-07-28

Zhicheng Huang, Zhaoyang Zeng, Yupan Huang, Bei Liu, Dongmei Fu, Jianlong Fu

We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient image regions and align regions with words step-by-step. As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages. In this paper, we propose SOHO to "See Out of tHe bOx" that takes a whole image as input, and learns vision-language representation in an end-to-end manner. SOHO does not require bounding box annotations which enables inference 10 times faster than region-based approaches. In particular, SOHO learns to extract comprehensive yet compact image features through a visual dictionary (VD) that facilitates cross-modal understanding. VD is designed to represent consistent visual abstractions of similar semantics. It is updated on-the-fly and utilized in our proposed pre-training task Masked Visual Modeling (MVM). We conduct experiments on four well-established vision-language tasks by following standard VLPT settings. In particular, SOHO achieves absolute gains of 2.0% R@1 score on MSCOCO text retrieval 5k test split, 1.5% accuracy on NLVR² test-P split, 6.7% accuracy on SNLI-VE test split, respectively.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

researchmm/soho officialmentioned in papermentioned on GitHubpytorch report
PasserBy4/mypretraining mentioned on GitHubpytorch report
PasserBy4/pretraining mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Representation LearningRetrievalText RetrievalVisual EntailmentVisual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Entailment SNLI-VE test SOHO Accuracy 84.95 #5 of 8 Archive leaderboard report
Visual Entailment SNLI-VE val SOHO Accuracy 85.00 #5 of 9 Archive leaderboard report
Visual Reasoning NLVR2 Dev SOHO Accuracy 76.37 #12 of 15 Archive leaderboard report
Visual Reasoning NLVR2 Test SOHO Accuracy 77.32 #12 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSOHOSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections